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
2018 年的期刊文章 · 第 33 页
共 1294 篇,按发表时间排,新的在前,每页 40 篇。这一页是 2018 到 2018。
按期刊、按主题看 →
JMLR Other · 发表于 2018
Brendan van Rooyen, Robert C. Williamson
摘要
It is usual in machine learning theory to assume that the training and testing sets comprise of draws from the same distribution. This is rarely, if ever, true and one must admit the presence of corruption. There are many different types of corruption that can arise and as of yet there is no general means to compare the relative ease of learning in these settings. Such results are necessary if we are to make informed economic decisions regarding the acquisition of data.
Econometrica Econometrics & Economics · 发表于 2018
Ezra Oberfield
摘要
Individual producers exhibit enormous heterogeneity in many dimensions. This paper develops a theory in which the network structure of production—who buys inputs from whom—forms endogenously. Entrepreneurs produce using labor and exactly one intermediate input; the key decision is which other entrepreneur's good to use as an input. Their choices collectively determine the economy's equilibrium input–output structure, generating large differences in size and shaping both individual and aggregate productivity. When the elasticity of output to intermediate inputs in production is high, star suppliers emerge endogenously. This raises aggregate productivity as, in equilibrium, more supply chains are routed through higher‐productivity techniques. *(abstract via OpenAlex)*
JMLR Other · 发表于 2018
Elif Vural, Christine Guillemot
摘要
Supervised manifold learning methods learn data representations by preserving the geometric structure of data while enhancing the separation between data samples from different classes. In this work, we propose a theoretical study of supervised manifold learning for classification. We consider nonlinear dimensionality reduction algorithms that yield linearly separable embeddings of training data and present generalization bounds for this type of algorithms. A necessary condition for satisfactory generalization performance is that the embedding allow the construction of a sufficiently regular interpolation function in relation with the separation margin of the embedding. We show that for supervised embeddings satisfying this condition, the classification error decays at an exponential rate with the number of training samples. Finally, we examine the separability of supervised nonlinear embeddings that aim to preserve the low-dimensional geometric structure of data based on graph representations. The proposed analysis is supported by experiments on several real data sets.
JMLR Spatial & Time Series · 发表于 2018
Bhavya Kailkhura, Jayaraman J. Thiagarajan, Charvi Rastogi, Pramod K. Varshney, Peer-Timo Bremer
摘要
This paper proposes a new approach to construct high quality space-filling sample designs. First, we propose a novel technique to quantify the space-filling property and optimally trade-off uniformity and randomness in sample designs in arbitrary dimensions. Second, we connect the proposed metric (defined in the spatial domain) to the quality metric of the design performance (defined in the spectral domain). This connection serves as an analytic framework for evaluating the qualitative properties of space-filling designs in general. Using the theoretical insights provided by this spatial-spectral analysis, we derive the notion of optimal space-filling designs, which we refer to as space-filling spectral designs. Third, we propose an efficient estimator to evaluate the space-filling properties of sample designs in arbitrary dimensions and use it to develop an optimization framework for generating high quality space-filling designs. Finally, we carry out a detailed performance comparison on two different applications in varying dimensions: a) image reconstruction and b) surrogate modeling for several benchmark optimization functions and a physics simulation code for inertial confinement fusion (ICF). Our results clearly evidence the superiority of the proposed space-filling designs over existing approaches, particularly in high dimensions.
JMLR Optimization & Learning Theory · 发表于 2018
Ruidi Chen, Ioannis Ch. Paschalidis
摘要
We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers. Our approach mitigates the impact of outliers by hedging against a family of probability distributions on the observed data, some of which assign very low probabilities to the outliers. The set of distributions under consideration are close to the empirical distribution in the sense of the Wasserstein metric. We show that this DRO formulation can be relaxed to a convex optimization problem which encompasses a class of models. By selecting proper norm spaces for the Wasserstein metric, we are able to recover several commonly used regularized regression models. We provide new insights into the regularization term and give guidance on the selection of the regularization coefficient from the standpoint of a confidence region. We establish two types of performance guarantees for the solution to our formulation under mild conditions. One is related to its out-of-sample behavior (prediction bias), and the other concerns the discrepancy between the estimated and true regression planes (estimation bias). Extensive numerical results demonstrate the superiority of our approach to a host of regression models, in terms of the prediction and estimation accuracies. We also consider the application of our robust learning procedure to outlier detection, and show that our approach achieves a much higher AUC (Area Under the ROC Curve) than M-estimation (Huber, 1964, 1973).
JMLR Other · 发表于 2018
Xiaoyi Mai
摘要
This article provides an original understanding of the behavior of a class of graph-oriented semi-supervised learning algorithms in the limit of large and numerous data. It is demonstrated that the intuition at the root of these methods collapses in this limit and that, as a result, most of them become inconsistent. Corrective measures and a new data-driven parametrization scheme are proposed along with a theoretical analysis of the asymptotic performances of the resulting approach. A surprisingly close behavior between theoretical performances on Gaussian mixture models and on real data sets is also illustrated throughout the article, thereby suggesting the importance of the proposed analysis for dealing with practical data. As a result, significant performance gains are observed on practical data classification using the proposed parametrization.
Econometrica High-Dimensional Testing & Uncertainty · 发表于 2018
A. Chudik, G. Kapetanios, M. Hashem Pesaran
摘要
This paper provides an alternative approach to penalized regression for model selection in the context of high‐dimensional linear regressions where the number of covariates is large, often much larger than the number of available observations. We consider the statistical significance of individual covariates one at a time, while taking full account of the multiple testing nature of the inferential problem involved. We refer to the proposed method as One Covariate at a Time Multiple Testing (OCMT) procedure, and use ideas from the multiple testing literature to control the probability of selecting the approximating model, the false positive rate, and the false discovery rate. OCMT is easy to interpret, relates to classical statistical analysis, is valid under general assumptions, is faster to compute, and performs well in small samples. The usefulness of OCMT is also illustrated by an empirical application to forecasting U.S. output growth and inflation. *(abstract via OpenAlex)*
JMLR High-Dimensional Networks & Graphs · 发表于 2018
Karl Rohe, Jun Tao, Xintian Han, Norbert Binkiewicz
摘要
Given matrices $X,Y \in R^{n \times K}$ and $S \in R^{K \times K}$ with positive elements, this paper proposes an algorithm fastRG to sample a sparse matrix $A$ with low rank expectation $E(A) = XSY^T$ and independent Poisson elements. This allows for quickly sampling from a broad class of stochastic blockmodel graphs (degree-corrected, mixed membership, overlapping) all of which are specific parameterizations of the generalized random product graph model defined in Section 2.2. The basic idea of fastRG is to first sample the number of edges $m$ and then sample each edge. The key insight is that because of the the low rank expectation, it is easy to sample individual edges. The naive “element-wise” algorithm requires $O(n^2)$ operations to generate the $n\times n$ adjacency matrix $A$. In sparse graphs, where $m = O(n)$, ignoring log terms, fastRG runs in time $O(n)$. An implementation in R is available on github. A computational experiment in Section 2.4 simulates graphs up to $n=10,000,000$ nodes with $m = 100,000,000$ edges. For example, on a graph with $n=500,000$ and $m = 5,000,000$, fastRG runs in less than one second on a 3.5 GHz Intel i5.
Econometrica Other · 发表于 2018
Michaela Pagel
摘要
Recent evidence suggests that investors are inattentive to their portfolios and hire expensive portfolio managers. This paper develops a life‐cycle portfolio‐choice model in which the investor experiences loss‐averse utility over news and can ignore his portfolio. In such a model, the investor prefers to ignore and not rebalance his portfolio most of the time because he dislikes bad news more than he likes good news such that expected news causes a first‐order decrease in utility. Consequently, the investor has a first‐order willingness to pay a portfolio manager who rebalances actively on his behalf. Moreover, the investor can diversify over time and his consumption aligns with predictions of mental accounting. I structurally estimate the preference parameters by matching stock shares and stock‐market non‐participation over the life cycle. My parameter estimates are in line with the literature, generate reasonable intervals of inattention, and simultaneously explain consumption and wealth accumulation over the life cycle. Here, it matters that news utility preserves first‐order risk aversion even in the presence of stochastic labor income, which also causes stock shares to rise in wealth. *(abstract via OpenAlex)*
JMLR Other · 发表于 2018
Ivo F. D. Oliveira, Nir Ailon, Ori Davidov
摘要
We consider the situation where $I$ items are ranked by paired comparisons. It is usually assumed that the probability that item $i$ is preferred over item $j$ is $p_{ij}=F(\mu_i-\mu_j)$ where $F$ is a symmetric distribution function, which we refer to as the comparison function, and $\mu_i$ and $\mu_j$ are the merits or scores of the compared items. This modelling framework, which is ubiquitous in the paired comparison literature, strongly depends on the assumption that the comparison function $F$ is known. In practice, however, this assumption is often unrealistic and may result in poor fit and erroneous inferences. This limitation has motivated us to relax the assumption that $F$ is fully known and simultaneously estimate the merits of the objects and the underlying comparison function. Our formulation yields a flexible semi-definite programming problem that we use as a refinement step for estimating the paired comparison probability matrix. We provide a detailed sensitivity analysis and, as a result, we establish the consistency of the resulting estimators and provide bounds on the estimation and approximation errors. Some statistical properties of the resulting estimators as well as model selection criteria are investigated. Finally, using a large data-set of computer chess matches, we estimate the comparison function and find that the model used by the International Chess Federation does not seem to apply to computer chess.
JMLR Survival Analysis · 发表于 2018
Ahmed M. Alaa, Mihaela van der Schaar
摘要
Modeling continuous-time physiological processes that manifest a patient's evolving clinical states is a key step in approaching many problems in healthcare. In this paper, we develop the Hidden Absorbing Semi-Markov Model (HASMM): a versatile probabilistic model that is capable of capturing the modern electronic health record (EHR) data. Unlike existing models, the HASMM accommodates irregularly sampled, temporally correlated, and informatively censored physiological data, and can describe non-stationary clinical state transitions. Learning the HASMM parameters from the EHR data is achieved via a novel forward-filtering backward-sampling Monte-Carlo EM algorithm that exploits the knowledge of the end-point clinical outcomes (informative censoring) in the EHR data, and implements the E-step by sequentially sampling the patients' clinical states in the reverse-time direction while conditioning on the future states. Real-time inferences are drawn via a forward-filtering algorithm that operates on a virtually constructed discrete-time embedded Markov chain that mirrors the patient's continuous-time state trajectory. We demonstrate the prognostic utility of the HASMM in a critical care prognosis setting using a real-world dataset for patients admitted to the Ronald Reagan UCLA Medical Center. In particular, we show that using HASMMs, a patient's clinical deterioration can be predicted 8-9 hours prior to intensive care unit admission, with a 22$\%$ AUC gain compared to the Rothman index, which is the state-of-the-art critical care risk scoring technology.
JMLR High-Dimensional · 发表于 2018
Binyan Jiang, Xiangyu Wang, Chenlei Leng
摘要
Quadratic discriminant analysis (QDA) is a standard tool for classification due to its simplicity and flexibility. Because the number of its parameters scales quadratically with the number of the variables, QDA is not practical, however, when the dimensionality is relatively large. To address this, we propose a novel procedure named DA-QDA for QDA in analyzing high-dimensional data. Formulated in a simple and coherent framework, DA-QDA aims to directly estimate the key quantities in the Bayes discriminant function including quadratic interactions and a linear index of the variables for classification. Under appropriate sparsity assumptions, we establish consistency results for estimating the interactions and the linear index, and further demonstrate that the misclassification rate of our procedure converges to the optimal Bayes risk, even when the dimensionality is exponentially high with respect to the sample size. An efficient algorithm based on the alternating direction method of multipliers (ADMM) is developed for finding interactions, which is much faster than its competitor in the literature. The promising performance of DA-QDA is illustrated via extensive simulation studies and the analysis of four real datasets.
JMLR High-Dimensional · 发表于 2018
Jian Huang, Yuling Jiao, Yanyan Liu, Xiliang Lu
摘要
We propose a constructive approach to estimating sparse, high-dimensional linear regression models. The approach is a computational algorithm motivated from the KKT conditions for the $\ell_0$-penalized least squares solutions. It generates a sequence of solutions iteratively, based on support detection using primal and dual information and root finding. We refer to the algorithm as SDAR for brevity. Under a sparse Riesz condition on the design matrix and certain other conditions, we show that with high probability, the $\ell_2$ estimation error of the solution sequence decays exponentially to the minimax error bound in $O(\log(R\sqrt{J}))$ iterations, where $J$ is the number of important predictors and $R$ is the relative magnitude of the nonzero target coefficients; and under a mutual coherence condition and certain other conditions, the $\ell_{\infty}$ estimation error decays to the optimal error bound in $O(\log(R))$ iterations. Moreover the SDAR solution recovers the oracle least squares estimator within a finite number of iterations with high probability if the sparsity level is known. Computational complexity analysis shows that the cost of SDAR is $O(np)$ per iteration. We also consider an adaptive version of SDAR for use in practical applications where the true sparsity level is unknown. Simulation studies demonstrate that SDAR outperforms Lasso, MCP and two greedy methods in accuracy and efficiency.
JMLR High-Dimensional · 发表于 2018
Bradley S. Price, Ben Sherwood
摘要
We propose a method for simultaneously estimating regression coefficients and clustering response variables in a multivariate regression model, to increase prediction accuracy and give insights into the relationship between response variables. The estimates of the regression coefficients and clusters are found by using a penalized likelihood estimator, which includes a cluster fusion penalty, to shrink the difference in fitted values from responses in the same cluster, and an $L_1$ penalty for simultaneous variable selection and estimation. We propose a two-step algorithm, that iterates between k-means clustering and solving the penalized likelihood function assuming the clusters are known, which has desirable parallel computational properties obtained by using the cluster fusion penalty. If the response variable clusters are known a priori then the algorithm reduces to just solving the penalized likelihood problem. Theoretical results are presented for the penalized least squares case, including asymptotic results allowing for $p \gg n$. We extend our method to the setting where the responses are binomial variables. We propose a coordinate descent algorithm for the normal likelihood and a proximal gradient descent algorithm for the binomial likelihood, which can easily be extended to other generalized linear model (GLM) settings. Simulations and data examples from business operations and genomics are presented to show the merits of both the least squares and binomial methods.