研究园简易版 · 经典书籍 · 期刊文章 · 有原文 · 完整版(可多选筛选、搜索) · 首页
2020 年的期刊文章 · 第 29 页
共 1467 篇,按发表时间排,新的在前,每页 40 篇。这一页是 2020-01-06 到 2020。
按期刊、按主题看 →
SiM Causal Inference · 发表于 2020-01-06
Michal Shauly‐Aharonov
摘要
In observational studies, it is agreed that the sensitivity of the findings to unmeasured confounders needs to be assessed. The issue is that a poor choice of test statistic can result in overstated sensitivity to hidden bias of this kind. In this article, a new adaptive test is proposed, guided by considerations of low sensitivity to hidden bias: it is tailored so that its power is greater than other leading tests, both in finite and infinite samples. One way of defining power in case of possible confounders is as the probability of reporting robustness (ie, insensitivity) of a true discovery to potential bias. In case of finite samples, we compute the power by simulations. When sample size approaches infinity, a meaningful indicator of the power is the design sensitivity, which is computed analytically and found to be better in the new test than in existing tests. Another asymptotic criterion for comparing tests when there is concern for confounders is Bahadur efficiency. The proposed test outperforms commonly used tests in terms of Bahadur efficiency in most sampling situations. The advantages of the new test mainly stem from its adaptivity: it combines two test statistics and consequently achieves the best design sensitivity and the best Bahadur efficiency of the two. As a “real‐world” examination, we compare 441 daily smokers to 441 nonsmokers, to test the effect of smoking on periodontal disease. The new test is more robust to unmeasured confounders than both the Wilcoxon signed rank test and the pairedt‐test.
Biometrics Survival Analysis Causal Inference · 发表于 2020-01-06
Erin E. Gabriel, Michael C. Sachs, Dean A. Follmann, Therese M‐L. Andersson
摘要
Many infectious diseases are well prevented by proper vaccination. However, when a vaccine is not completely efficacious, there is great interest in determining how the vaccine effect differs in subgroups conditional on measured immune responses postvaccination and also according to the type of infecting agent (eg, strain of a virus). The former is often called correlate of protection (CoP) analysis, while the latter has been called sieve analysis. We propose a unified framework for simultaneously assessing CoP and sieve effects of a vaccine in a large Phase III randomized trial. We use flexible parametric models treating times to infection from different agents as competing risks and estimated maximum likelihood to fit the models. The parametric models under competing risks allow for estimation of both cumulative incidence‐based contrasts and instantaneous rates. We outline the assumptions with which we can link the observable data to the causal contrasts of interest, propose hypothesis testing procedures, and evaluate our proposed methods in an extensive simulation study.
Biometrics Missing Data & Measurement Error Testing & Uncertainty · 发表于 2020-01-06
DongHyuk Lee, Soumendra N. Lahiri, Samiran Sinha
摘要
When the observed data are contaminated with errors, the standard two‐sample testing approaches that ignore measurement errors may produce misleading results, including a higher type‐I error rate than the nominal level. To tackle this inconsistency, a nonparametric test is proposed for testing equality of two distributions when the observed contaminated data follow the classical additive measurement error model. The proposed test takes into account the presence of errors in the observed data, and the test statistic is defined in terms of the (deconvoluted) characteristic functions of the latent variables. Proposed method is applicable to a wide range of scenarios as no parametric restrictions are imposed either on the distribution of the underlying latent variables or on the distribution of the measurement errors. Asymptotic null distribution of the test statistic is derived, which is given by an integral of a squared Gaussian process with a complicated covariance structure. For data‐based calibration of the test, a new nonparametric Bootstrap method is developed under the two‐sample measurement error framework and its validity is established. Finite sample performance of the proposed test is investigated through simulation studies, and the results show superior performance of the proposed method than the standard tests that exhibit inconsistent behavior. Finally, the proposed method was applied to real data sets from the National Health and Nutrition Examination Survey. An R package MEtest is available through CRAN.
JASA Bayesian Methods Latent Variables & Mixtures · 发表于 2020-01-06
Changgee Chang, Jeong Hoon Jang, Amita Manatunga, Andrew T. Taylor, Qi Long
摘要
Kidney obstruction, if untreated in a timely manner, can lead to irreversible loss of renal function. A widely used technology for evaluations of kidneys with suspected obstruction is diuresis renography. However, it is generally very challenging for radiologists who typically interpret renography data in practice to build high level of competency due to the low volume of renography studies and insufficient training. Another challenge is that there is currently no gold standard for detection of kidney obstruction. Seeking to develop a computer-aided diagnostic (CAD) tool that can assist practicing radiologists to reduce errors in the interpretation of kidney obstruction, a recent study collected data from diuresis renography, interpretations on the renography data from highly experienced nuclear medicine experts as well as clinical data. To achieve the objective, we develop a statistical model that can be used as a CAD tool for assisting radiologists in kidney interpretation. We use a Bayesian latent class modeling approach for predicting kidney obstruction through the integrative analysis of time-series renogram data, expert ratings, and clinical variables. A nonparametric Bayesian latent factor regression approach is adopted for modeling renogram curves in which the coefficients of the basis functions are parameterized via the factor loadings dependent on the latent disease status and the extended latent factors that can also adjust for clinical variables. A hierarchical probit model is used for expert ratings, allowing for training with rating data from multiple experts while predicting with at most one expert, which makes the proposed model operable in practice. An efficient MCMC algorithm is developed to train the model and predict kidney obstruction with associated uncertainty. We demonstrate the superiority of the proposed method over several existing methods through extensive simulations. Analysis of the renal study also lends support to the usefulness of our model as a CAD tool to assist less experienced radiologists in the field. *(abstract via PubMed)*
JASA Econometrics & Economics · 发表于 2020-01-03
Dachuan Chen, Per A. Mykland, Lan Zhang
摘要
We develop a principal component analysis (PCA) for high frequency data. As in Northern fairy tales, there are trolls waiting for the explorer. The first three trolls are market microstructure noise, asynchronous sampling times, and edge effects in estimators. To get around these, a robust estimator of the spot covariance matrix is developed based on the smoothed two-scale realized variance (S-TSRV). The fourth troll is how to pass from estimated time-varying covariance matrix to PCA. Under finite dimensionality, we develop this methodology through the estimation of realized spectral functions. Rates of convergence and central limit theory, as well as an estimator of standard error, are established. The fifth troll is high dimension on top of high frequency, where we also develop PCA. With the help of a new identity concerning the spot principal orthogonal complement, the high-dimensional rates of convergence have been studied after eliminating several strong assumptions in classical PCA. As an application, we show that our first principal component (PC) closely matches but potentially outperforms the S&P 100 market index. From a statistical standpoint, the close match between the first PC and the market index also corroborates this PCA procedure and the underlying S-TSRV matrix, in the sense of Karl Popper. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA Other · 发表于 2020-01-03
Yixin Wang, David M. Blei
摘要
We thank all the discussants for taking the time and energy to build on this work; and we thank the editors for putting together an engaging and thought-provoking collection of discussions. After r... *(abstract via OpenAlex)*
JASA Causal Inference Machine Learning · 发表于 2020-01-03
Yixin Wang, David M. Blei
摘要
Causal inference from observational data is a vital problem, but it comes with strong assumptions. Most methods assume that we observe all confounders, variables that affect both the causal variables and the outcome variables. This assumption is standard but it is also untestable. In this article, we develop the deconfounder, a way to do causal inference with weaker assumptions than the traditional methods require. The deconfounder is designed for problems of multiple causal inference: scientific studies that involve multiple causes whose effects are simultaneously of interest. Specifically, the deconfounder combines unsupervised machine learning and predictive model checking to use the dependencies among multiple causes as indirect evidence for some of the unobserved confounders. We develop the deconfounder algorithm, prove that it is unbiased, and show that it requires weaker assumptions than traditional causal inference. We analyze its performance in three types of studies: semi-simulated data around smoking and lung cancer, semi-simulated data around genome-wide association studies, and a real dataset about actors and movie revenue. The deconfounder is an effective approach to estimating causal effects in problems of multiple causal inference. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA Econometrics & Economics · 发表于 2020-01-03
Ben Dai, Xiaotong Shen, Junhui Wang, Annie Qu
摘要
Ben Daiab, Xiaotong Shena, Junhui Wangb & Annie Quc* a School of Statistics, University of Minnesota , Minneapolis , MN ; b School of Data Science, City University of Hong Kong , Kowloon Tong, Hong Kong ; c Department of Statistics, University of Illinois at Urbana Champaign , Champaign , IL Supplementary materials for this article are available online. Please go to www.tandfonline.com/r/JASA. CONTACT Annie Qu anniequ@illinois.edu Department of Statistics, University of Illinois at Urbana Champaign , Champaign , IL 61820.AbstractPersonalized prediction presents an important yet challenging task, which predicts user-specific preferences on a large number of items given limited information. It is often modeled as certain recommender systems focusing on ordinal or continuous ratings, as in collaborative filtering and content-based filtering. In this article, we propose a new collaborative ranking system to predict most-preferred items for each user given search queries. Particularly, we propose a ψ-ranker based on ranking functions incorporating information on users, items, and search queries through latent factor models. Moreover, we show that the proposed nonconvex surrogate pairwise ψ-loss performs well under four popular bipartite ranking losses, such as the sum loss, pairwise zero-one loss, discounted cumulative gain, and mean average precision. We develop a parallel computing strategy to optimize the intractable loss of two levels of nonconvex components through difference of convex programming and block successive upper-bound minimization. Theoretically, we establish a probabilistic error bound for the ψ-ranker and show that its ranking error has a sharp rate of convergence in the general framework of bipartite ranking, even when the dimension of the model parameters diverges with the sample size. Consequently, this result also indicates that the ψ-ranker performs better than two major approaches in bipartite ranking: pairwise ranking and scoring. Finally, we demonstrate the utility of the ψ-ranker by comparing it with some strong competitors in the literature through simulated examples as well as Expedia booking data. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA Causal Inference Bayesian Methods Nonparametric & Semiparametric · 发表于 2020-01-03
Samrachana Adhikari, Sherri Rose, Sharon-Lise Normand
摘要
Percutaneous coronary interventions (PCIs) are nonsurgical procedures to open blocked blood vessels to the heart, frequently using a catheter to place a stent. The catheter can be inserted into the blood vessels using an artery in the groin or an artery in the wrist. Because clinical trials have indicated that access via the wrist may result in fewer post procedure complications, shortening the length of stay, and ultimately cost less than groin access, adoption of access via the wrist has been encouraged. However, patients treated in usual care are likely to differ from those participating in clinical trials, and there is reason to believe that the effectiveness of wrist access may differ between males and females. Moreover, the choice of artery access strategy is likely to be influenced by patient or physician unmeasured factors. To study the effectiveness of the two artery access site strategies on hospitalization charges, we use data from a state-mandated clinical registry including 7,963 patients undergoing PCI. A hierarchical Bayesian likelihood-based instrumental variable analysis under a latent index modeling framework is introduced to jointly model outcomes and treatment status. Our approach accounts for unobserved heterogeneity via a latent factor structure, and permits nonparametric error distributions with Dirichlet process mixture models. Our results demonstrate that artery access in the wrist reduces hospitalization charges compared to access in the groin, with a higher mean reduction for male patients. *(abstract via PubMed)*
JASA Other · 发表于 2020-01-03
A. Alexandre Trindade
摘要
This book presents procedures for making statistical inferences on the basis of the classical linear statistical model, and discusses the various properties of those procedures. Supporting material... *(abstract via OpenAlex)*
JASA High-Dimensional Longitudinal Data · 发表于 2020-01-03
Jelena Bradic, Gerda Claeskens, Thomas Gueuning
摘要
Many scientific and engineering challenges—ranging from pharmacokinetic drug dosage allocation and personalized medicine to marketing mix (4Ps) recommendations—require an understanding of the unobserved heterogeneity to develop the best decision making-processes. In this article, we develop a hypothesis test and the corresponding p-value for testing for the significance of the homogeneous structure in linear mixed models. A robust matching moment construction is used for creating a test that adapts to the size of the model sparsity. When unobserved heterogeneity at a cluster level is constant, we show that our test is both consistent and unbiased even when the dimension of the model is extremely high. Our theoretical results rely on a new family of adaptive sparse estimators of the fixed effects that do not require consistent estimation of the random effects. Moreover, our inference results do not require consistent model selection. We showcase that moment matching can be extended to nonlinear mixed effects models and to generalized linear mixed effects models. In numerical and real data experiments, we find that the developed method is extremely accurate, that it adapts to the size of the underlying model and is decidedly powerful in the presence of irrelevant covariates. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA Other · 发表于 2020-01-03
Lisa Morrissey LaVange
摘要
Color versions of one or more of the figures in the article can be found online at www.tandfonline.com/r/JASA.Abstract–Each year, the Journal of the American Statistical Association publishes the presidential address from the Joint Statistical Meetings. Here we present the 2018 address verbatim save for the addition of references and a few minor editorial corrections. *(abstract via OpenAlex)*
JASA Latent Variables & Mixtures Machine Learning Optimization & Learning Theory · 发表于 2020-01-03
Yixuan Qiu, Xiao Wang
摘要
Latent variable models cover a broad range of statistical and machine learning models, such as Bayesian models, linear mixed models, and Gaussian mixture models. Existing methods often suffer from two major challenges in practice: (a) a proper latent variable distribution is difficult to be specified; (b) making an exact likelihood inference is formidable due to the intractable computation. We propose a novel framework for the inference of latent variable models that overcomes these two limitations. This new framework allows for a fully data-driven latent variable distribution via deep neural networks, and the proposed stochastic gradient method, combined with the Langevin algorithm, is efficient and suitable for complex models and big data. We provide theoretical results for the Langevin algorithm, and establish the convergence analysis of the optimization method. This framework has demonstrated superior practical performance through simulation studies and a real data analysis. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
Biometrics Diagnostics & Prediction Survival Analysis · 发表于 2020-01-02
Yei Eun Shin, Ruth M. Pfeiffer, Barry I. Graubard, Mitchell H. Gail
摘要
Cohort studies provide information on relative hazards and pure risks of disease. For rare outcomes, large cohorts are needed to have sufficient numbers of events, making it costly to obtain covariate information on all cohort members. We focus on nested case‐control designs that are used to estimate relative hazard in the Cox regression model. In 1997, Langholz and Borgan showed that pure risk can also be estimated from nested case‐control data. However, these approaches do not take advantage of some covariates that may be available on all cohort members. Researchers have used weight calibration to increase the efficiency of relative hazard estimates from case‐cohort studies and nested cased‐control studies. Our objective is to extend weight calibration approaches to nested case‐control designs to improve precision of estimates of relative hazards and pure risks. We show that calibrating sample weights additionally against follow‐up times multiplied by relative hazards during the risk projection period improves estimates of pure risk. Efficiency improvements for relative hazards for variables that are available on the entire cohort also contribute to improved efficiency for pure risks. We develop explicit variance formulas for the weight‐calibrated estimates. Simulations show how much precision is improved by calibration and confirm the validity of inference based on asymptotic normality. Examples are provided using data from the American Association of Retired Persons Diet and Health Cohort Study.
Biometrics Clinical Trials · 发表于 2020-01-02
Dateng Li, Jing Cao, Song Zhang
摘要
Cluster randomized trials (CRTs) are widely used in different areas of medicine and public health. Recently, with increasing complexity of medical therapies and technological advances in monitoring multiple outcomes, many clinical trials attempt to evaluate multiple co‐primary endpoints. In this study, we present a power analysis method for CRTs with binary co‐primary endpoints. It is developed based on the GEE (generalized estimating equation) approach, and three types of correlations are considered: inter‐subject correlation within each endpoint, intra‐subject correlation across endpoints, and inter‐subject correlation across endpoints. A closed‐form joint distribution of the K test statistics is derived, which facilitates the evaluation of power and type I error for arbitrarily constructed hypotheses. We further present a theorem that characterizes the relationship between various correlations and testing power. We assess the performance of the proposed power analysis method based on extensive simulation studies. An application example to a real clinical trial is presented.
JMLR Survival Analysis · 发表于 2020
Sebastian Pölsterl
摘要
scikit-survival is an open-source Python package for time-to-event analysis fully compatible with scikit-learn. It provides implementations of many popular machine learning techniques for time-to-event analysis, including penalized Cox model, Random Survival Forest, and Survival Support Vector Machine. In addition, the library includes tools to evaluate model performance on censored time-to-event data. The documentation contains installation instructions, interactive notebooks, and a full description of the API. scikit-survival is distributed under the GPL-3 license with the source code and detailed instructions available at https://github.com/sebp/scikit-survival
JMLR Spatial & Time Series · 发表于 2020
Johann Faouzi, Hicham Janati
摘要
pyts is an open-source Python package for time series classification. This versatile toolbox provides implementations of many algorithms published in the literature, preprocessing functionalities, and data set loading utilities. pyts relies on the standard scientific Python packages numpy, scipy, scikit-learn, joblib, and numba, and is distributed under the BSD-3-Clause license. Documentation contains installation instructions, a detailed user guide, a full API description, and concrete self-contained examples.
JMLR Nonparametric & Semiparametric · 发表于 2020
Juan Luis Suárez, Salvador García, Francisco Herrera
摘要
pyDML is an open-source python library that provides a wide range of distance metric learning algorithms. Distance metric learning can be useful to improve similarity learning algorithms, such as the nearest neighbors classifier, and also has other applications, like dimensionality reduction. The pyDML package currently provides more than 20 algorithms, which can be categorized, according to their purpose, in: dimensionality reduction algorithms, algorithms to improve nearest neighbors or nearest centroids classifiers, information theory based algorithms or kernel based algorithms, among others. In addition, the library also provides some utilities for the visualization of classifier regions, parameter tuning and a stats website with the performance of the implemented algorithms. The package relies on the scipy ecosystem, it is fully compatible with scikit-learn, and is distributed under GPLv3 license. Source code and documentation can be found at https://github.com/jlsuarezdiaz/pyDML.
JMLR Other · 发表于 2020
William de Vazelhes, CJ Carey, Yuan Tang, Nathalie Vauquier, Aurélien Bellet
摘要
metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms. As part of scikit-learn-contrib, it provides a unified interface compatible with scikit-learn which allows to easily perform cross-validation, model selection, and pipelining with other machine learning estimators. metric-learn is thoroughly tested and available on PyPi under the MIT license.
JMLR Other · 发表于 2020
Jacob Schreiber, Jeffrey Bilmes, William Stafford Noble
摘要
We present apricot, an open source Python package for selecting representative subsets from large data sets using submodular optimization. The package implements several efficient greedy selection algorithms that offer strong theoretical guarantees on the quality of the selected set. Additionally, several submodular set functions are implemented, including facility location, which is broadly applicable but requires memory quadratic in the number of examples in the data set, and a feature-based function that is less broadly applicable but can scale to millions of examples. Apricot is extremely efficient, using both algorithmic speedups such as the lazy greedy algorithm and memoization as well as code optimization using numba. We demonstrate the use of subset selection by training machine learning models to comparable accuracy using either the full data set or a representative subset thereof. This paper presents an explanation of submodular selection, an overview of the features in apricot, and applications to two data sets.
JMLR Networks & Graphs · 发表于 2020
Joseph D. Ramsey, Daniel Malinsky, Kevin V. Bui
摘要
In this report we describe a tool for comparing the performance of graphical causal structure learning algorithms implemented in the TETRAD freeware suite of causal analysis methods. Currently the tool is available as package in the TETRAD source code (written in Java). Simulations can be done varying the number of runs, sample sizes, and data modalities. Performance on this simulated data can then be compared for a number of algorithms, with parameters varied and with performance statistics as selected, producing a publishable report. The package presented here may also be used to compare structure learning methods across platforms and programming languages, i.e., to compare algorithms implemented in TETRAD with those implemented in MATLAB, Python, or R.
JMLR Networks & Graphs Machine Learning Nonparametric & Semiparametric · 发表于 2020
Devanshu Agrawal, Theodore Papamarkou, Jacob Hinkle
摘要
There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not apply to architectures that require one or more of the hidden layers to remain narrow. In this paper, we consider the wide limit of BNNs where some hidden layers, called "bottlenecks", are held at finite width. The result is a composition of GPs that we term a "bottleneck neural network Gaussian process" (bottleneck NNGP). Although intuitive, the subtlety of the proof is in showing that the wide limit of a composition of networks is in fact the composition of the limiting GPs. We also analyze theoretically a single-bottleneck NNGP, finding that the bottleneck induces dependence between the outputs of a multi-output network that persists through extreme post-bottleneck depths, and prevents the kernel of the network from losing discriminative power at extreme post-bottleneck depths.
Econometrica Nonparametric & Semiparametric Econometrics & Economics · 发表于 2020
Matthew Backus
摘要
The correlation between productivity and competition is an oft observed but incompletely understood result. Some suggest that there is a treatment effect of competition on measured productivity, for example, through a reduction of managerial slack. Others argue that greater competition makes unproductive establishments exit by reallocating demand to their productive rivals, raising observed average productivity via selection. I study the ready‐mix concrete industry and offer three perspectives on this ambivalence. First, using a standard decomposition approach, I look for evidence of greater reallocation of demand to productive plants in more competitive markets. Second, I model the establishment exit decision and construct a semiparametric selection correction to quantify the empirical significance of treatment and selection. Finally, I use a grouped instrumental variable quantile regression to test the distributional predictions of the selection hypothesis. I find no evidence for greater selection or reallocation in more competitive markets; instead, all three results suggest that measured productivity responds directly to competition. Potential channels include specialization and managerial inputs.
JMLR Missing Data & Measurement Error · 发表于 2020
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin
摘要
We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighted message passing algorithm to reconstruct labels for SBM based on the minimum energy flow and the eigenvectors of a certain Markov transition matrix. The general SBM considered in this paper allows for unequal-size communities, degree heterogeneity, and different connection probabilities among blocks. We focus on how to optimally weigh the message passing to improve misclassification.
JMLR Meta-Analysis & Data Integration High-Dimensional · 发表于 2020
Edgar Dobriban, Yue Sheng
摘要
In many areas, practitioners need to analyze large data sets that challenge conventional single-machine computing. To scale up data analysis, distributed and parallel computing approaches are increasingly needed. Here we study a fundamental and highly important problem in this area: How to do ridge regression in a distributed computing environment? Ridge regression is an extremely popular method for supervised learning, and has several optimality properties, thus it is important to study. We study one-shot methods that construct weighted combinations of ridge regression estimators computed on each machine. By analyzing the mean squared error in a high-dimensional random-effects model where each predictor has a small effect, we discover several new phenomena. Infinite-worker limit: The distributed estimator works well for very large numbers of machines, a phenomenon we call 'infinite-worker limit'. Optimal weights: The optimal weights for combining local estimators sum to more than unity, due to the downward bias of ridge. Thus, all averaging methods are suboptimal. We also propose a new Weighted ONe-shot DistributEd Ridge regression algorithm (WONDER). We test WONDER in simulation studies and using the Million Song Dataset as an example. There it can save at least 100x in computation time, while nearly preserving test accuracy.
JMLR Bayesian Methods Machine Learning · 发表于 2020
Francesco Tonolini, Jack Radford, Alex Turpin, Daniele Faccio, Roderick Murray-Smith
摘要
Machine learning methods for computational imaging require uncertainty estimation to be reliable in real settings. While Bayesian models offer a computationally tractable way of recovering uncertainty, they need large data volumes to be trained, which in imaging applications implicates prohibitively expensive collections with specific imaging instruments. This paper introduces a novel framework to train variational inference for inverse problems exploiting in combination few experimentally collected data, domain expertise and existing image data sets. In such a way, Bayesian machine learning models can solve imaging inverse problems with minimal data collection efforts. Extensive simulated experiments show the advantages of the proposed framework. The approach is then applied to two real experimental optics settings: holographic image reconstruction and imaging through highly scattering media. In both settings, state of the art reconstructions are achieved with little collection of training data.
JMLR Networks & Graphs Latent Variables & Mixtures · 发表于 2020
Zhuang Ma, Zongming Ma, Hongsong Yuan
摘要
Latent space models are effective tools for statistical modeling and visualization of network data. Due to their close connection to generalized linear models, it is also natural to incorporate covariate information in them. The current paper presents two universal fitting algorithms for networks with edge covariates: one based on nuclear norm penalization and the other based on projected gradient descent. Both algorithms are motivated by maximizing the likelihood function for an existing class of inner-product models, and we establish their statistical rates of convergence for these models. In addition, the theory informs us that both methods work simultaneously for a wide range of different latent space models that allow latent positions to affect edge formation in flexible ways, such as distance models. Furthermore, the effectiveness of the methods is demonstrated on a number of real world network data sets for different statistical tasks, including community detection with and without edge covariates, and network assisted learning.
JMLR Other · 发表于 2020
Yu Wang, Siqi Wu, Bin Yu
摘要
We study the problem of globally recovering a dictionary from a set of signals via $\ell_1$-minimization. We assume that the signals are generated as i.i.d. random linear combinations of the $K$ atoms from a complete reference dictionary $D^*\in \mathbb R^{K\times K}$, where the linear combination coefficients are from either a Bernoulli type model or exact sparse model. First, we obtain a necessary and sufficient norm condition for the reference dictionary $D^*$ to be a sharp local minimum of the expected $\ell_1$ objective function. Our result substantially extends that of Wu and Yu (2015) and allows the combination coefficient to be non-negative. Secondly, we obtain an explicit bound on the region within which the objective value of the reference dictionary is minimal. Thirdly, we show that the reference dictionary is the unique sharp local minimum, thus establishing the first known global property of $\ell_1$-minimization dictionary learning. Motivated by the theoretical results, we introduce a perturbation based test to determine whether a dictionary is a sharp local minimum of the objective function. In addition, we also propose a new dictionary learning algorithm based on Block Coordinate Descent, called DL-BCD, which is guaranteed to decrease the obective function monotonically. Simulation studies show that DL-BCD has competitive performance in terms of recovery rate compared to other state-of-the-art dictionary learning algorithms when the reference dictionary is generated from random Gaussian matrices.
JMLR Latent Variables & Mixtures · 发表于 2020
Morteza Ashraphijuo, Xiaodong Wang
摘要
We consider the problem of clustering and completing a set of tensors with missing data that are drawn from a union of low-rank tensor spaces. In the clustering problem, given a partially sampled tensor data that is composed of a number of subtensors, each chosen from one of a certain number of unknown tensor spaces, we need to group the subtensors that belong to the same tensor space. We provide a geometrical analysis on the sampling pattern and subsequently derive the sampling rate that guarantees the correct clustering under some assumptions with high probability. Moreover, we investigate the fundamental conditions for finite/unique completability for the union of tensor spaces completion problem. Both deterministic and probabilistic conditions on the sampling pattern to ensure finite/unique completability are obtained. For both the clustering and completion problems, our tensor analysis provides significantly better bound than the bound given by the matrix analysis applied to any unfolding of the tensor data.
Econometrica Econometrics & Economics · 发表于 2020
Sushant Acharya, Keshav Dogra
摘要
Using an analytically tractable heterogeneous agent New Keynesian model, we show that whether incomplete markets resolve New Keynesian “paradoxes” depends on the cyclicality of income risk. Incomplete markets reduce the effectiveness of forward guidance and multipliers in a liquidity trap only with procyclical risk. Countercyclical risk amplifies these “puzzles.” Procyclical risk permits determinacy under a peg; countercyclical risk may generate indeterminacy even under the Taylor principle. By affecting the cyclicality of risk, even “passive” fiscal policy influences the effects of monetary policy.
Econometrica Other · 发表于 2020
Janet M. Currie, W. Bentley MacLeod
摘要
Treatment for depression is complex, requiring decisions that may involve trade‐offs between exploiting treatments with the highest expected value and experimenting with treatments with higher possible payoffs. Using patient claims data, we show that among skilled doctors, using a broader portfolio of drugs predicts better patient outcomes, except in cases where doctors' decisions violate loose professional guidelines. We introduce a behavioral model of decision making guided by our empirical observations. The model's novel feature is that the trade‐off between exploitation and experimentation depends on the doctor's diagnostic skill. The model predicts that higher diagnostic skill leads to greater diversity in drug choice and better matching of drugs to patients even among doctors with the same initial beliefs regarding drug effectiveness. Consistent with the finding that guideline violations predict poorer patient outcomes, simulations of the model suggest that increasing the number of possible drug choices can lower performance.
Econometrica Econometrics & Economics Causal Inference · 发表于 2020
Nathan Canen, Chad Kendall, Francesco Trebbi
摘要
This paper investigates the determinants of political polarization, a phenomenon of increasing relevance in Western democracies. How much of polarization is driven by divergence in the ideologies of politicians? How much is instead the result of changes in the capacity of parties to control their members? We use detailed internal information on party discipline in the context of the U.S. Congress—whip count data for 1977–1986—to identify and structurally estimate an economic model of legislative activity in which agenda selection, party discipline, and member votes are endogenous. The model delivers estimates of the ideological preferences of politicians, the extent of party control, and allows us to assess the effects of polarization through agenda setting (i.e., which alternatives to a status quo are strategically pursued). We find that parties account for approximately 40% of the political polarization in legislative voting over this time period, a critical inflection point in U.S. polarization. We also show that, absent party control, historically significant economic policies would have not passed or lost substantial support. Counterfactual exercises establish that party control is highly relevant for the probability of success of a given bill and that polarization in ideological preferences is more consequential for policy selection, resulting in different bills being pursued.
JMLR High-Dimensional Nonparametric & Semiparametric · 发表于 2020
Yuankun Zhang, Heng Lian, Yan Yu
摘要
We consider a flexible semiparametric single-index quantile regression model where the number of covariates may be ultra-high dimensional, and the number of the relevant covariates is potentially diverging. The approach is particularly appealing to uncover the complex heterogeneity in high-dimensional data, incorporate nonlinearity and potential interaction, avoid the curse of dimensionality, and allow different variables to be included at different quantile levels. We estimate the unknown function via polynomial splines nonparametrically and adopt a nonconvex penalty function to identify the sparse variable set. We further extend it to partially linear single-index quantile model where both the single-index components in the nonparametric term and the partially linear components can be in ultra-high dimension. However, a number of major challenges arise in developing both theory and computation: (a) The model is highly nonlinear in single-index coefficients because the high-dimensional single-index covariates are embedded inside the unknown flexible function. (b) The data are ultra-high dimensional where the dimension of the single-index covariates ($p_n$) is diverging or even in the exponential order of sample size $n$. (c) The objective function is non-smooth for quantile regression. (d) Nonconvex variable selection such as SCAD is adopted for regularization. (e) The extended partially linear single-index quantile models may include both ultra-high dimensional ($p_n$) single-index covariates and ultra-high dimensional ($q_n$) partially linear covariates. We develop a novel approach using empirical process techniques in establishing the theoretical properties of the nonconvex penalized estimators for partially linear single-index quantile models and show those estimators indeed possess the oracle property in ultra-high dimensional setting. We propose an efficient algorithm to circumvent the computational challenges. The results of Monte Carlo simulations and an application to gene expression data demonstrate the effectiveness of the proposed models and estimation method.
JMLR High-Dimensional · 发表于 2020
Martin Slawski, Emanuel Ben-David, Ping Li
摘要
A tacit assumption in linear regression is that (response, predictor)-pairs correspond to identical observational units. A series of recent works have studied scenarios in which this assumption is violated under terms such as “Unlabeled Sensing and “Regression with Unknown Permutation”. In this paper, we study the setup of multiple response variables and a notion of mismatches that generalizes permutations in order to allow for missing matches as well as for one-to-many matches. A two-stage method is proposed under the assumption that most pairs are correctly matched. In the first stage, the regression parameter is estimated by handling mismatches as contaminations, and subsequently the generalized permutation is estimated by a basic variant of matching. The approach is both computationally convenient and equipped with favorable statistical guarantees. Specifically, it is shown that the conditions for permutation recovery become considerably less stringent as the number of responses $m$ per observation increase. Particularly, for $m = \Omega(\log n)$, the required signal-to-noise ratio no longer depends on the sample size $n$. Numerical results on synthetic and real data are presented to support the main findings of our analysis.
JMLR Bayesian Methods Optimization & Learning Theory · 发表于 2020
Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria, Christopher R. Collins, Jeff Schneider, Barnabas Poczos, Eric P. Xing
摘要
Bayesian Optimisation (BO) refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently search for the optimum. While BO has been applied successfully in many applications, modern optimisation tasks usher in new challenges where conventional methods fail spectacularly. In this work, we present Dragonfly, an open source Python library for scalable and robust BO. Dragonfly incorporates multiple recently developed methods that allow BO to be applied in challenging real world settings; these include better methods for handling higher dimensional domains, methods for handling multi-fidelity evaluations when cheap approximations of an expensive function are available, methods for optimising over structured combinatorial spaces, such as the space of neural network architectures, and methods for handling parallel evaluations. Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and additional constraints. We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO. The Dragonfly library is available at dragonfly.github.io.
JMLR Machine Learning Spatial & Time Series Meta-Analysis & Data Integration · 发表于 2020
Romain Tavenard, Johann Faouzi, Gilles Vandewiele, Felix Divo, Guillaume Androz, Chester Holtz, Marie Payne, Roman Yurchak, Marc Rußwurm, Kushal Kolar, Eli Woods
摘要
tslearn is a general-purpose Python machine learning library for time series that offers tools for pre-processing and feature extraction as well as dedicated models for clustering, classification and regression. It follows scikit-learn's Application Programming Interface for transformers and estimators, allowing the use of standard pipelines and model selection tools on top of tslearn objects. It is distributed under the BSD-2-Clause license, and its source code is available at https://github.com/tslearn-team/tslearn.
JMLR Bayesian Methods Latent Variables & Mixtures · 发表于 2020
Oleg Arenz, Mingjun Zhong, Gerhard Neumann
摘要
Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and careful exploration of the relevant modes of the target distribution. We propose a method for learning accurate GMM approximations of intractable probability distributions based on insights from policy search by using information-geometric trust regions for principled exploration. For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently. Our use of the lower bound ensures convergence to a stationary point of the original objective. The number of components is adapted online by adding new components in promising regions and by deleting components with negligible weight. We demonstrate on several domains that we can learn approximations of complex, multimodal distributions with a quality that is unmet by previous variational inference methods, and that the GMM approximation can be used for drawing samples that are on par with samples created by state-of-the-art MCMC samplers while requiring up to three orders of magnitude less computational resources.
Econometrica Econometrics & Economics · 发表于 2020
Ariel Burstein, Gordon Hanson, Lin Tian, Jonathan Vogel
摘要
In this paper, we study how occupation (or industry) tradability shapes local labor‐market adjustment to immigration. Theoretically, we derive a simple condition under which the arrival of foreign‐born labor into a region crowds native‐born workers out of (or into) immigrant‐intensive jobs, thus lowering (or raising) relative wages in these occupations, and we explain why this process differs within tradable versus within nontradable activities. Using data for U.S. commuting zones over the period 1980–2012, we find—consistent with our theory—that a local influx of immigrants crowds out employment of native‐born workers in more relative to less immigrant‐intensive nontradable jobs, but has no such effect across tradable occupations. Further analysis of occupation labor payments is consistent with adjustment to immigration within tradables occurring more through changes in output (versus changes in prices) when compared to adjustment within nontradables, thereby confirming our model's theoretical mechanism. We then use the model to explore the quantitative consequences of counterfactual changes in U.S. immigration on real wages at the occupation and region level.
JMLR Machine Learning · 发表于 2020
Vardan Papyan
摘要
Numerous researchers recently applied empirical spectral analysis to the study of modern deep learning classifiers. We identify and discuss an important formal class/cross-class structure and show how it lies at the origin of the many visually striking features observed in deep neural network spectra, some of which were reported in recent articles, others are unveiled here for the first time. These include spectral outliers, “spikes”, and small but distinct continuous distributions, “bumps”, often seen beyond the edge of a “main bulk”.
JMLR Machine Learning · 发表于 2020
Peter Henderson, Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, Joelle Pineau
摘要
Accurate reporting of energy and carbon usage is essential for understanding the potential climate impacts of machine learning research. We introduce a framework that makes this easier by providing a simple interface for tracking realtime energy consumption and carbon emissions, as well as generating standardized online appendices. Utilizing this framework, we create a leaderboard for energy efficient reinforcement learning algorithms to incentivize responsible research in this area as an example for other areas of machine learning. Finally, based on case studies using our framework, we propose strategies for mitigation of carbon emissions and reduction of energy consumption. By making accounting easier, we hope to further the sustainable development of machine learning experiments and spur more research into energy efficient algorithms.