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
2022 年 · JMLR
Journal of Machine Learning Research,2022 年发表的 353 篇,新的在前。点标题看作者和摘要。回到 2022 年
- tntorch: Tensor Network Learning with PyTorch · JMLR · 2022 · 在第 27 页
- solo-learn: A Library of Self-supervised Methods for Visual Representation Learning · JMLR · 2022 · 在第 27 页
- ktrain: A Low-Code Library for Augmented Machine Learning · JMLR · 2022 · 在第 27 页
- d3rlpy: An Offline Deep Reinforcement Learning Library · JMLR · 2022 · 在第 27 页
- abess: A Fast Best-Subset Selection Library in Python and R · JMLR · 2022 · 在第 27 页
- XAI Beyond Classification: Interpretable Neural Clustering · JMLR · 2022 · 在第 27 页
- When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint · JMLR · 2022 · 在第 27 页
- When Hardness of Approximation Meets Hardness of Learning · JMLR · 2022 · 在第 27 页
- Weakly Supervised Disentangled Generative Causal Representation Learning · JMLR · 2022 · 在第 27 页
- WarpDrive: Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU · JMLR · 2022 · 在第 27 页
- Vector-Valued Least-Squares Regression under Output Regularity Assumptions · JMLR · 2022 · 在第 27 页
- Variational Inference in high-dimensional linear regression · JMLR · 2022 · 在第 27 页
- Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization · JMLR · 2022 · 在第 27 页
- Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features · JMLR · 2022 · 在第 27 页
- Using Active Queries to Infer Symmetric Node Functions of Graph Dynamical Systems · JMLR · 2022 · 在第 27 页
- Unlabeled Data Help in Graph-Based Semi-Supervised Learning: A Bayesian Nonparametrics Perspective · JMLR · 2022 · 在第 27 页
- Universal Approximation of Functions on Sets · JMLR · 2022 · 在第 27 页
- Universal Approximation in Dropout Neural Networks · JMLR · 2022 · 在第 27 页
- Universal Approximation Theorems for Differentiable Geometric Deep Learning · JMLR · 2022 · 在第 27 页
- Uniform deconvolution for Poisson Point Processes · JMLR · 2022 · 在第 27 页
- Underspecification Presents Challenges for Credibility in Modern Machine Learning · JMLR · 2022 · 在第 27 页
- Under-bagging Nearest Neighbors for Imbalanced Classification · JMLR · 2022 · 在第 27 页
- Unbiased estimators for random design regression · JMLR · 2022 · 在第 27 页
- Two-mode Networks: Inference with as Many Parameters as Actors and Differential Privacy · JMLR · 2022 · 在第 27 页
- Two-Sample Testing on Ranked Preference Data and the Role of Modeling Assumptions · JMLR · 2022 · 在第 27 页
- Truncated Emphatic Temporal Difference Methods for Prediction and Control · JMLR · 2022 · 在第 27 页
- Tree-based Node Aggregation in Sparse Graphical Models · JMLR · 2022 · 在第 27 页
- Tree-Values: Selective Inference for Regression Trees · JMLR · 2022 · 在第 27 页
- Tree-Based Models for Correlated Data · JMLR · 2022 · 在第 27 页
- Transfer Learning in Information Criteria-based Feature Selection · JMLR · 2022 · 在第 27 页
- Training and Evaluation of Deep Policies Using Reinforcement Learning and Generative Models · JMLR · 2022 · 在第 27 页
- Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent · JMLR · 2022 · 在第 27 页
- Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration · JMLR · 2022 · 在第 27 页
- Towards An Efficient Approach for the Nonconvex lp Ball Projection: Algorithm and Analysis · JMLR · 2022 · 在第 27 页
- Toward Understanding Convolutional Neural Networks from Volterra Convolution Perspective · JMLR · 2022 · 在第 28 页
- Total Stability of SVMs and Localized SVMs · JMLR · 2022 · 在第 28 页
- Topologically penalized regression on manifolds · JMLR · 2022 · 在第 28 页
- Toolbox for Multimodal Learn (scikit-multimodallearn) · JMLR · 2022 · 在第 28 页
- Tianshou: A Highly Modularized Deep Reinforcement Learning Library · JMLR · 2022 · 在第 28 页
- Three rates of convergence or separation via U-statistics in a dependent framework · JMLR · 2022 · 在第 28 页
- Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data · JMLR · 2022 · 在第 28 页
- Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning · JMLR · 2022 · 在第 28 页
- The Weighted Generalised Covariance Measure · JMLR · 2022 · 在第 28 页
- The Two-Sided Game of Googol · JMLR · 2022 · 在第 28 页
- The Separation Capacity of Random Neural Networks · JMLR · 2022 · 在第 28 页
- The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks · JMLR · 2022 · 在第 28 页
- The Importance of Being Correlated: Implications of Dependence in Joint Spectral Inference across Multiple Networks · JMLR · 2022 · 在第 28 页
- The Geometry of Uniqueness, Sparsity and Clustering in Penalized Estimation · JMLR · 2022 · 在第 28 页
- The EM Algorithm is Adaptively-Optimal for Unbalanced Symmetric Gaussian Mixtures · JMLR · 2022 · 在第 28 页
- The Correlation-assisted Missing Data Estimator · JMLR · 2022 · 在第 28 页
- The AIM and EM Algorithms for Learning from Coarse Data · JMLR · 2022 · 在第 28 页
- Testing Whether a Learning Procedure is Calibrated · JMLR · 2022 · 在第 28 页
- TFPnP: Tuning-free Plug-and-Play Proximal Algorithms with Applications to Inverse Imaging Problems · JMLR · 2022 · 在第 28 页
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity · JMLR · 2022 · 在第 28 页
- Supervised Dimensionality Reduction and Visualization using Centroid-Encoder · JMLR · 2022 · 在第 28 页
- Sum of Ranked Range Loss for Supervised Learning · JMLR · 2022 · 在第 28 页
- Sufficient reductions in regression with mixed predictors · JMLR · 2022 · 在第 28 页
- Structure-adaptive Manifold Estimation · JMLR · 2022 · 在第 28 页
- Structure Learning for Directed Trees · JMLR · 2022 · 在第 28 页
- Structural Agnostic Modeling: Adversarial Learning of Causal Graphs · JMLR · 2022 · 在第 28 页
- Stochastic subgradient for composite convex optimization with functional constraints · JMLR · 2022 · 在第 28 页
- Stochastic Zeroth-Order Optimization under Nonstationarity and Nonconvexity · JMLR · 2022 · 在第 28 页
- Stochastic DCA with Variance Reduction and Applications in Machine Learning · JMLR · 2022 · 在第 28 页
- Statistical Rates of Convergence for Functional Partially Linear Support Vector Machines for Classification · JMLR · 2022 · 在第 28 页
- Statistical Optimality and Stability of Tangent Transform Algorithms in Logit Models · JMLR · 2022 · 在第 29 页
- Statistical Optimality and Computational Efficiency of Nystrom Kernel PCA · JMLR · 2022 · 在第 29 页
- Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriors · JMLR · 2022 · 在第 29 页
- Stable Classification · JMLR · 2022 · 在第 29 页
- Spatial Multivariate Trees for Big Data Bayesian Regression · JMLR · 2022 · 在第 29 页
- Sparse Continuous Distributions and Fenchel-Young Losses · JMLR · 2022 · 在第 29 页
- Sparse Additive Gaussian Process Regression · JMLR · 2022 · 在第 29 页
- Solving Large-Scale Sparse PCA to Certifiable (Near) Optimality · JMLR · 2022 · 在第 29 页
- Solving L1-regularized SVMs and Related Linear Programs: Revisiting the Effectiveness of Column and Constraint Generation · JMLR · 2022 · 在第 29 页
- Smooth Robust Tensor Completion for Background/Foreground Separation with Missing Pixels: Novel Algorithm with Convergence Guarantee · JMLR · 2022 · 在第 29 页
- Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization · JMLR · 2022 · 在第 29 页
- Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States · JMLR · 2022 · 在第 29 页
- Signature Moments to Characterize Laws of Stochastic Processes · JMLR · 2022 · 在第 29 页
- Semiparametric Inference For Causal Effects In Graphical Models With Hidden Variables · JMLR · 2022 · 在第 29 页
- Self-Healing Robust Neural Networks via Closed-Loop Control · JMLR · 2022 · 在第 29 页
- Selective Machine Learning of the Average Treatment Effect with an Invalid Instrumental Variable · JMLR · 2022 · 在第 29 页
- Score Matched Neural Exponential Families for Likelihood-Free Inference · JMLR · 2022 · 在第 29 页
- Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters · JMLR · 2022 · 在第 29 页
- Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements · JMLR · 2022 · 在第 29 页
- Scaling Laws from the Data Manifold Dimension · JMLR · 2022 · 在第 29 页
- Scalable and Efficient Hypothesis Testing with Random Forests · JMLR · 2022 · 在第 29 页
- Scalable Gaussian-process regression and variable selection using Vecchia approximations · JMLR · 2022 · 在第 29 页
- Sampling Permutations for Shapley Value Estimation · JMLR · 2022 · 在第 29 页
- SODEN: A Scalable Continuous-Time Survival Model through Ordinary Differential Equation Networks · JMLR · 2022 · 在第 29 页
- SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization · JMLR · 2022 · 在第 29 页
- SGD with Coordinate Sampling: Theory and Practice · JMLR · 2022 · 在第 29 页
- Robust and scalable manifold learning via landmark diffusion for long-term medical signal processing · JMLR · 2022 · 在第 29 页
- Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks · JMLR · 2022 · 在第 29 页
- Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold · JMLR · 2022 · 在第 29 页
- Reverse-mode differentiation in arbitrary tensor network format: with application to supervised learning · JMLR · 2022 · 在第 29 页
- Rethinking Nonlinear Instrumental Variable Models through Prediction Validity · JMLR · 2022 · 在第 29 页
- ReservoirComputing.jl: An Efficient and Modular Library for Reservoir Computing Models · JMLR · 2022 · 在第 29 页
- Representation Learning for Maximization of MI, Nonlinear ICA and Nonlinear Subspaces with Robust Density Ratio Estimation · JMLR · 2022 · 在第 29 页
- Regularized and Smooth Double Core Tensor Factorization for Heterogeneous Data · JMLR · 2022 · 在第 29 页
- Regularized K-means Through Hard-Thresholding · JMLR · 2022 · 在第 30 页
- ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction · JMLR · 2022 · 在第 30 页
- Recovery and Generalization in Over-Realized Dictionary Learning · JMLR · 2022 · 在第 30 页
- Recovering shared structure from multiple networks with unknown edge distributions · JMLR · 2022 · 在第 30 页
- Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs · JMLR · 2022 · 在第 30 页
- Quantile regression with ReLU Networks: Estimators and minimax rates · JMLR · 2022 · 在第 30 页
- Provable Tensor-Train Format Tensor Completion by Riemannian Optimization · JMLR · 2022 · 在第 30 页
- Projection-free Distributed Online Learning with Sublinear Communication Complexity · JMLR · 2022 · 在第 30 页
- Projected Statistical Methods for Distributional Data on the Real Line with the Wasserstein Metric · JMLR · 2022 · 在第 30 页
- Projected Robust PCA with Application to Smooth Image Recovery · JMLR · 2022 · 在第 30 页
- Project and Forget: Solving Large-Scale Metric Constrained Problems · JMLR · 2022 · 在第 30 页
- Prior Adaptive Semi-supervised Learning with Application to EHR Phenotyping · JMLR · 2022 · 在第 30 页
- Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks · JMLR · 2022 · 在第 30 页
- Power Iteration for Tensor PCA · JMLR · 2022 · 在第 30 页
- Posterior Asymptotics for Boosted Hierarchical Dirichlet Process Mixtures · JMLR · 2022 · 在第 30 页
- Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms · JMLR · 2022 · 在第 30 页
- Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach · JMLR · 2022 · 在第 30 页
- Pathfinder: Parallel quasi-Newton variational inference · JMLR · 2022 · 在第 30 页
- PECOS: Prediction for Enormous and Correlated Output Spaces · JMLR · 2022 · 在第 30 页
- PAC Guarantees and Effective Algorithms for Detecting Novel Categories · JMLR · 2022 · 在第 30 页
- Overparameterization of Deep ResNet: Zero Loss and Mean-field Analysis · JMLR · 2022 · 在第 30 页
- Oracle Complexity in Nonsmooth Nonconvex Optimization · JMLR · 2022 · 在第 30 页
- Optimality and Stability in Non-Convex Smooth Games · JMLR · 2022 · 在第 30 页
- Optimal Transport for Stationary Markov Chains via Policy Iteration · JMLR · 2022 · 在第 30 页
- Online Nonnegative CP-dictionary Learning for Markovian Data · JMLR · 2022 · 在第 30 页
- Online Mirror Descent and Dual Averaging: Keeping Pace in the Dynamic Case · JMLR · 2022 · 在第 30 页
- On the Robustness to Misspecification of α-posteriors and Their Variational Approximations · JMLR · 2022 · 在第 30 页
- On the Efficiency of Entropic Regularized Algorithms for Optimal Transport · JMLR · 2022 · 在第 31 页
- On the Convergence Rates of Policy Gradient Methods · JMLR · 2022 · 在第 31 页
- On the Complexity of Approximating Multimarginal Optimal Transport · JMLR · 2022 · 在第 31 页
- On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC) · JMLR · 2022 · 在第 31 页
- On quantitative Laplace-type convergence results for some exponential probability measures, with two applications · JMLR · 2022 · 在第 31 页
- On Regularized Square-root Regression Problems: Distributionally Robust Interpretation and Fast Computations · JMLR · 2022 · 在第 31 页
- On Mixup Regularization · JMLR · 2022 · 在第 31 页
- On Low-rank Trace Regression under General Sampling Distribution · JMLR · 2022 · 在第 31 页
- On Instrumental Variable Regression for Deep Offline Policy Evaluation · JMLR · 2022 · 在第 31 页
- On Generalizations of Some Distance Based Classifiers for HDLSS Data · JMLR · 2022 · 在第 31 页
- On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems · JMLR · 2022 · 在第 31 页
- On Biased Stochastic Gradient Estimation · JMLR · 2022 · 在第 31 页
- On Acceleration for Convex Composite Minimization with Noise-Corrupted Gradients and Approximate Proximal Mapping · JMLR · 2022 · 在第 31 页
- OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems · JMLR · 2022 · 在第 31 页
- OMLT: Optimization & Machine Learning Toolkit · JMLR · 2022 · 在第 31 页
- Nystrom Regularization for Time Series Forecasting · JMLR · 2022 · 在第 31 页
- Novel Min-Max Reformulations of Linear Inverse Problems · JMLR · 2022 · 在第 31 页
- Nonstochastic Bandits with Composite Anonymous Feedback · JMLR · 2022 · 在第 31 页
- Nonparametric adaptive control and prediction: theory and randomized algorithms · JMLR · 2022 · 在第 31 页
- Nonparametric Principal Subspace Regression · JMLR · 2022 · 在第 31 页
- Nonparametric Neighborhood Selection in Graphical Models · JMLR · 2022 · 在第 31 页
- Nonconvex Matrix Completion with Linearly Parameterized Factors · JMLR · 2022 · 在第 31 页
- Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems · JMLR · 2022 · 在第 31 页
- Non-asymptotic Properties of Individualized Treatment Rules from Sequentially Rule-Adaptive Trials · JMLR · 2022 · 在第 31 页
- No Weighted-Regret Learning in Adversarial Bandits with Delays · JMLR · 2022 · 在第 31 页
- New Insights for the Multivariate Square-Root Lasso · JMLR · 2022 · 在第 31 页
- Neural Estimation of Statistical Divergences · JMLR · 2022 · 在第 31 页
- Network Regression with Graph Laplacians · JMLR · 2022 · 在第 31 页
- Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes · JMLR · 2022 · 在第 31 页
- Mutual Information Constraints for Monte-Carlo Objectives to Prevent Posterior Collapse Especially in Language Modelling · JMLR · 2022 · 在第 31 页
- MurTree: Optimal Decision Trees via Dynamic Programming and Search · JMLR · 2022 · 在第 31 页
- Multivariate Boosted Trees and Applications to Forecasting and Control · JMLR · 2022 · 在第 31 页
- Multiple-Splitting Projection Test for High-Dimensional Mean Vectors · JMLR · 2022 · 在第 31 页
- Multiple Testing in Nonparametric Hidden Markov Models: An Empirical Bayes Approach · JMLR · 2022 · 在第 31 页
- Multi-Task Dynamical Systems · JMLR · 2022 · 在第 31 页
- Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism · JMLR · 2022 · 在第 31 页
- Multi-Agent Multi-Armed Bandits with Limited Communication · JMLR · 2022 · 在第 31 页
- More Powerful Conditional Selective Inference for Generalized Lasso by Parametric Programming · JMLR · 2022 · 在第 31 页
- Model Averaging Is Asymptotically Better Than Model Selection For Prediction · JMLR · 2022 · 在第 32 页
- Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables · JMLR · 2022 · 在第 32 页
- Minimax optimal approaches to the label shift problem in non-parametric settings · JMLR · 2022 · 在第 32 页
- Minimax Mixing Time of the Metropolis-Adjusted Langevin Algorithm for Log-Concave Sampling · JMLR · 2022 · 在第 32 页
- Metrics of Calibration for Probabilistic Predictions · JMLR · 2022 · 在第 32 页
- Meta-analysis of heterogeneous data: integrative sparse regression in high-dimensions · JMLR · 2022 · 在第 32 页
- Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks · JMLR · 2022 · 在第 32 页
- Maximum sampled conditional likelihood for informative subsampling · JMLR · 2022 · 在第 32 页
- Matrix Completion with Covariate Information and Informative Missingness · JMLR · 2022 · 在第 32 页
- Mappings for Marginal Probabilities with Applications to Models in Statistical Physics · JMLR · 2022 · 在第 32 页
- Manifold Coordinates with Physical Meaning · JMLR · 2022 · 在第 32 页
- Machine Learning on Graphs: A Model and Comprehensive Taxonomy · JMLR · 2022 · 在第 32 页
- MALTS: Matching After Learning to Stretch · JMLR · 2022 · 在第 32 页
- Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization · JMLR · 2022 · 在第 32 页
- Logarithmic Regret for Episodic Continuous-Time Linear-Quadratic Reinforcement Learning over a Finite-Time Horizon · JMLR · 2022 · 在第 32 页
- Linearization and Identification of Multiple-Attractor Dynamical Systems through Laplacian Eigenmaps · JMLR · 2022 · 在第 32 页
- LinCDE: Conditional Density Estimation via Lindsey's Method · JMLR · 2022 · 在第 32 页
- Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence · JMLR · 2022 · 在第 32 页
- Learning to Optimize: A Primer and A Benchmark · JMLR · 2022 · 在第 32 页
- Learning linear non-Gaussian directed acyclic graph with diverging number of nodes · JMLR · 2022 · 在第 32 页
- Learning from Noisy Pairwise Similarity and Unlabeled Data · JMLR · 2022 · 在第 32 页
- Learning Temporal Evolution of Spatial Dependence with Generalized Spatiotemporal Gaussian Process Models · JMLR · 2022 · 在第 32 页
- Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training · JMLR · 2022 · 在第 32 页
- Learning Operators with Coupled Attention · JMLR · 2022 · 在第 32 页
- Learning Green's functions associated with time-dependent partial differential equations · JMLR · 2022 · 在第 32 页
- LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data · JMLR · 2022 · 在第 33 页
- KoPA: Automated Kronecker Product Approximation · JMLR · 2022 · 在第 33 页
- Kernel Partial Correlation Coefficient --- a Measure of Conditional Dependence · JMLR · 2022 · 在第 33 页
- Kernel Packet: An Exact and Scalable Algorithm for Gaussian Process Regression with Matérn Correlations · JMLR · 2022 · 在第 33 页
- Kernel Autocovariance Operators of Stationary Processes: Estimation and Convergence · JMLR · 2022 · 在第 33 页
- KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints · JMLR · 2022 · 在第 33 页
- Jump Gaussian Process Model for Estimating Piecewise Continuous Regression Functions · JMLR · 2022 · 在第 33 页
- JsonGrinder.jl: automated differentiable neural architecture for embedding arbitrary JSON data · JMLR · 2022 · 在第 33 页
- Joint Inference of Multiple Graphs from Matrix Polynomials · JMLR · 2022 · 在第 33 页
- Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models · JMLR · 2022 · 在第 33 页
- Joint Continuous and Discrete Model Selection via Submodularity · JMLR · 2022 · 在第 33 页
- Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning · JMLR · 2022 · 在第 33 页
- Intrinsic Dimension Estimation Using Wasserstein Distance · JMLR · 2022 · 在第 33 页
- Interval-censored Hawkes processes · JMLR · 2022 · 在第 33 页
- Interpretable Classification of Categorical Time Series Using the Spectral Envelope and Optimal Scalings · JMLR · 2022 · 在第 33 页
- InterpretDL: Explaining Deep Models in PaddlePaddle · JMLR · 2022 · 在第 33 页
- Interpolating Predictors in High-Dimensional Factor Regression · JMLR · 2022 · 在第 33 页
- Interlocking Backpropagation: Improving depthwise model-parallelism · JMLR · 2022 · 在第 33 页
- Integral Autoencoder Network for Discretization-Invariant Learning · JMLR · 2022 · 在第 33 页
- Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection · JMLR · 2022 · 在第 33 页
- Inherent Tradeoffs in Learning Fair Representations · JMLR · 2022 · 在第 33 页
- Information-theoretic Classification Accuracy: A Criterion that Guides Data-driven Combination of Ambiguous Outcome Labels in Multi-class Classification · JMLR · 2022 · 在第 33 页
- Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning · JMLR · 2022 · 在第 33 页
- Improving Bayesian Network Structure Learning in the Presence of Measurement Error · JMLR · 2022 · 在第 33 页
- Improved Generalization Bounds for Adversarially Robust Learning · JMLR · 2022 · 在第 33 页
- Improved Classification Rates for Localized SVMs · JMLR · 2022 · 在第 33 页
- Implicit Differentiation for Fast Hyperparameter Selection in Non-Smooth Convex Learning · JMLR · 2022 · 在第 33 页
- IALE: Imitating Active Learner Ensembles · JMLR · 2022 · 在第 33 页
- Handling Hard Affine SDP Shape Constraints in RKHSs · JMLR · 2022 · 在第 33 页
- Hamilton-Jacobi equations on graphs with applications to semi-supervised learning and data depth · JMLR · 2022 · 在第 33 页
- Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences · JMLR · 2022 · 在第 33 页
- Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks · JMLR · 2022 · 在第 33 页
- Globally Injective ReLU Networks · JMLR · 2022 · 在第 33 页
- Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch · JMLR · 2022 · 在第 33 页
- Getting Better from Worse: Augmented Bagging and A Cautionary Tale of Variable Importance · JMLR · 2022 · 在第 34 页
- Generalized Sparse Additive Models · JMLR · 2022 · 在第 34 页
- Generalized Resubstitution for Classification Error Estimation · JMLR · 2022 · 在第 34 页
- Generalized Matrix Factorization: efficient algorithms for fitting generalized linear latent variable models to large data arrays · JMLR · 2022 · 在第 34 页
- Generalized Ambiguity Decomposition for Ranking Ensemble Learning · JMLR · 2022 · 在第 34 页
- Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects · JMLR · 2022 · 在第 34 页
- Gaussian process regression: Optimality, robustness, and relationship with kernel ridge regression · JMLR · 2022 · 在第 34 页
- Gaussian Process Parameter Estimation Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits · JMLR · 2022 · 在第 34 页
- Gaussian Process Boosting · JMLR · 2022 · 在第 34 页
- Gauss-Legendre Features for Gaussian Process Regression · JMLR · 2022 · 在第 34 页
- Fundamental Limits and Tradeoffs in Invariant Representation Learning · JMLR · 2022 · 在第 34 页
- Functional Linear Regression with Mixed Predictors · JMLR · 2022 · 在第 34 页
- Fully General Online Imitation Learning · JMLR · 2022 · 在第 34 页
- FuDGE: A Method to Estimate a Functional Differential Graph in a High-Dimensional Setting · JMLR · 2022 · 在第 34 页
- Foolish Crowds Support Benign Overfitting · JMLR · 2022 · 在第 34 页
- Faster Randomized Interior Point Methods for Tall/Wide Linear Programs · JMLR · 2022 · 在第 34 页
- Fast and Robust Rank Aggregation against Model Misspecification · JMLR · 2022 · 在第 34 页
- Fast Stagewise Sparse Factor Regression · JMLR · 2022 · 在第 34 页
- Fairness-Aware PAC Learning from Corrupted Data · JMLR · 2022 · 在第 34 页
- Extensions to the Proximal Distance Method of Constrained Optimization · JMLR · 2022 · 在第 34 页
- Exploiting locality in high-dimensional Factorial hidden Markov models · JMLR · 2022 · 在第 34 页
- Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods · JMLR · 2022 · 在第 34 页
- Expected Regret and Pseudo-Regret are Equivalent When the Optimal Arm is Unique · JMLR · 2022 · 在第 34 页
- Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks · JMLR · 2022 · 在第 34 页
- Exact simulation of diffusion first exit times: algorithm acceleration · JMLR · 2022 · 在第 34 页
- Exact Partitioning of High-order Models with a Novel Convex Tensor Cone Relaxation · JMLR · 2022 · 在第 34 页
- Evolutionary Variational Optimization of Generative Models · JMLR · 2022 · 在第 34 页
- Estimation and inference on high-dimensional individualized treatment rule in observational data using split-and-pooled de-correlated score · JMLR · 2022 · 在第 34 页
- Estimating Density Models with Truncation Boundaries using Score Matching · JMLR · 2022 · 在第 34 页
- Estimating Causal Effects under Network Interference with Bayesian Generalized Propensity Scores · JMLR · 2022 · 在第 34 页
- Empirical Risk Minimization under Random Censorship · JMLR · 2022 · 在第 34 页
- EiGLasso for Scalable Sparse Kronecker-Sum Inverse Covariance Estimation · JMLR · 2022 · 在第 35 页
- Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting · JMLR · 2022 · 在第 35 页
- Efficient Least Squares for Estimating Total Effects under Linearity and Causal Sufficiency · JMLR · 2022 · 在第 35 页
- Efficient Inference for Dynamic Flexible Interactions of Neural Populations · JMLR · 2022 · 在第 35 页
- Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits · JMLR · 2022 · 在第 35 页
- Early Stopping for Iterative Regularization with General Loss Functions · JMLR · 2022 · 在第 35 页
- EV-GAN: Simulation of extreme events with ReLU neural networks · JMLR · 2022 · 在第 35 页
- DoubleML - An Object-Oriented Implementation of Double Machine Learning in Python · JMLR · 2022 · 在第 35 页
- Double Spike Dirichlet Priors for Structured Weighting · JMLR · 2022 · 在第 35 页
- Distributional Random Forests: Heterogeneity Adjustment and Multivariate Distributional Regression · JMLR · 2022 · 在第 35 页
- Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima · JMLR · 2022 · 在第 35 页
- Distributed Learning of Finite Gaussian Mixtures · JMLR · 2022 · 在第 35 页
- Distributed Bootstrap for Simultaneous Inference Under High Dimensionality · JMLR · 2022 · 在第 35 页
- Distributed Bayesian Varying Coefficient Modeling Using a Gaussian Process Prior · JMLR · 2022 · 在第 35 页
- Detecting Latent Communities in Network Formation Models · JMLR · 2022 · 在第 35 页
- Depth separation beyond radial functions · JMLR · 2022 · 在第 35 页
- Dependent randomized rounding for clustering and partition systems with knapsack constraints · JMLR · 2022 · 在第 35 页
- Deepchecks: A Library for Testing and Validating Machine Learning Models and Data · JMLR · 2022 · 在第 35 页
- Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons · JMLR · 2022 · 在第 35 页
- Deep Limits and a Cut-Off Phenomenon for Neural Networks · JMLR · 2022 · 在第 35 页
- Deep Learning in Target Space · JMLR · 2022 · 在第 35 页
- Decimated Framelet System on Graphs and Fast G-Framelet Transforms · JMLR · 2022 · 在第 35 页
- Debiased Distributed Learning for Sparse Partial Linear Models in High Dimensions · JMLR · 2022 · 在第 35 页
- De-Sequentialized Monte Carlo: a parallel-in-time particle smoother · JMLR · 2022 · 在第 35 页
- Data-Derived Weak Universal Consistency · JMLR · 2022 · 在第 35 页
- Darts: User-Friendly Modern Machine Learning for Time Series · JMLR · 2022 · 在第 35 页
- D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data · JMLR · 2022 · 在第 35 页
- Convergence Rates for Gaussian Mixtures of Experts · JMLR · 2022 · 在第 35 页
- Convergence Guarantees for the Good-Turing Estimator · JMLR · 2022 · 在第 35 页
- Contraction rates for sparse variational approximations in Gaussian process regression · JMLR · 2022 · 在第 35 页
- Constraint Reasoning Embedded Structured Prediction · JMLR · 2022 · 在第 35 页
- Conditions and Assumptions for Constraint-based Causal Structure Learning · JMLR · 2022 · 在第 35 页
- Community detection in sparse latent space models · JMLR · 2022 · 在第 35 页
- Communication-Constrained Distributed Quantile Regression with Optimal Statistical Guarantees · JMLR · 2022 · 在第 35 页
- Clustering with Semidefinite Programming and Fixed Point Iteration · JMLR · 2022 · 在第 35 页
- CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms · JMLR · 2022 · 在第 36 页
- Change point localization in dependent dynamic nonparametric random dot product graphs · JMLR · 2022 · 在第 36 页
- Causal Classification: Treatment Effect Estimation vs. Outcome Prediction · JMLR · 2022 · 在第 36 页
- Causal Aggregation: Estimation and Inference of Causal Effects by Constraint-Based Data Fusion · JMLR · 2022 · 在第 36 页
- Cauchy–Schwarz Regularized Autoencoder · JMLR · 2022 · 在第 36 页
- Cascaded Diffusion Models for High Fidelity Image Generation · JMLR · 2022 · 在第 36 页
- CD-split and HPD-split: Efficient Conformal Regions in High Dimensions · JMLR · 2022 · 在第 36 页
- Bounding the Error of Discretized Langevin Algorithms for Non-Strongly Log-Concave Targets · JMLR · 2022 · 在第 36 页
- Boulevard: Regularized Stochastic Gradient Boosted Trees and Their Limiting Distribution · JMLR · 2022 · 在第 36 页
- Beyond Sub-Gaussian Noises: Sharp Concentration Analysis for Stochastic Gradient Descent · JMLR · 2022 · 在第 36 页
- Behavior Priors for Efficient Reinforcement Learning · JMLR · 2022 · 在第 36 页
- Bayesian subset selection and variable importance for interpretable prediction and classification · JMLR · 2022 · 在第 36 页
- Bayesian Pseudo Posterior Mechanism under Asymptotic Differential Privacy · JMLR · 2022 · 在第 36 页
- Bayesian Multinomial Logistic Normal Models through Marginally Latent Matrix-T Processes · JMLR · 2022 · 在第 36 页
- Bayesian Covariate-Dependent Gaussian Graphical Models with Varying Structure · JMLR · 2022 · 在第 36 页
- Batch Normalization Preconditioning for Neural Network Training · JMLR · 2022 · 在第 36 页
- Averaging Spatio-temporal Signals using Optimal Transport and Soft Alignment · JMLR · 2022 · 在第 36 页
- Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning · JMLR · 2022 · 在第 36 页
- Attraction-Repulsion Spectrum in Neighbor Embeddings · JMLR · 2022 · 在第 36 页
- Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape · JMLR · 2022 · 在第 36 页
- Asymptotic Network Independence and Step-Size for a Distributed Subgradient Method · JMLR · 2022 · 在第 36 页
- Asymptotic Analysis of Sampling Estimators for Randomized Numerical Linear Algebra Algorithms · JMLR · 2022 · 在第 36 页
- Are All Layers Created Equal? · JMLR · 2022 · 在第 36 页
- Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks · JMLR · 2022 · 在第 36 页
- Approximate Information State for Approximate Planning and Reinforcement Learning in Partially Observed Systems · JMLR · 2022 · 在第 36 页
- Approximate Bayesian Computation via Classification · JMLR · 2022 · 在第 36 页
- Analytically Tractable Hidden-States Inference in Bayesian Neural Networks · JMLR · 2022 · 在第 36 页
- An Optimization-centric View on Bayes' Rule: Reviewing and Generalizing Variational Inference · JMLR · 2022 · 在第 36 页
- An Improper Estimator with Optimal Excess Risk in Misspecified Density Estimation and Logistic Regression · JMLR · 2022 · 在第 36 页
- An Error Analysis of Generative Adversarial Networks for Learning Distributions · JMLR · 2022 · 在第 36 页
- An Efficient Sampling Algorithm for Non-smooth Composite Potentials · JMLR · 2022 · 在第 36 页
- All You Need is a Good Functional Prior for Bayesian Deep Learning · JMLR · 2022 · 在第 36 页
- Adversarial Robustness Guarantees for Gaussian Processes · JMLR · 2022 · 在第 37 页
- Adversarial Classification: Necessary Conditions and Geometric Flows · JMLR · 2022 · 在第 37 页
- Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces · JMLR · 2022 · 在第 37 页
- Additive Nonlinear Quantile Regression in Ultra-high Dimension · JMLR · 2022 · 在第 37 页
- Adaptive Greedy Algorithm for Moderately Large Dimensions in Kernel Conditional Density Estimation · JMLR · 2022 · 在第 37 页
- Active Structure Learning of Bayesian Networks in an Observational Setting · JMLR · 2022 · 在第 37 页
- Active Learning for Nonlinear System Identification with Guarantees · JMLR · 2022 · 在第 37 页
- Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling · JMLR · 2022 · 在第 37 页
- Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization · JMLR · 2022 · 在第 37 页
- ALMA: Alternating Minimization Algorithm for Clustering Mixture Multilayer Network · JMLR · 2022 · 在第 37 页
- A universally consistent learning rule with a universally monotone error · JMLR · 2022 · 在第 37 页
- A spectral-based analysis of the separation between two-layer neural networks and linear methods · JMLR · 2022 · 在第 37 页
- A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions · JMLR · 2022 · 在第 37 页
- A Worst Case Analysis of Calibrated Label Ranking Multi-label Classification Method · JMLR · 2022 · 在第 37 页
- A Wasserstein Distance Approach for Concentration of Empirical Risk Estimates · JMLR · 2022 · 在第 37 页
- A Unifying Framework for Variance-Reduced Algorithms for Findings Zeroes of Monotone operators · JMLR · 2022 · 在第 37 页
- A Unified Statistical Learning Model for Rankings and Scores with Application to Grant Panel Review · JMLR · 2022 · 在第 37 页
- A Stochastic Bundle Method for Interpolation · JMLR · 2022 · 在第 37 页
- A Statistical Approach for Optimal Topic Model Identification · JMLR · 2022 · 在第 37 页
- A Random Matrix Perspective on Random Tensors · JMLR · 2022 · 在第 37 页
- A Primer for Neural Arithmetic Logic Modules · JMLR · 2022 · 在第 37 页
- A Perturbation-Based Kernel Approximation Framework · JMLR · 2022 · 在第 37 页
- A Nonconvex Framework for Structured Dynamic Covariance Recovery · JMLR · 2022 · 在第 37 页
- A Momentumized, Adaptive, Dual Averaged Gradient Method · JMLR · 2022 · 在第 37 页
- A Kernel Two-Sample Test for Functional Data · JMLR · 2022 · 在第 37 页
- A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning · JMLR · 2022 · 在第 37 页
- A Forward Approach for Sufficient Dimension Reduction in Binary Classification · JMLR · 2022 · 在第 37 页
- A Distribution Free Conditional Independence Test with Applications to Causal Discovery · JMLR · 2022 · 在第 37 页
- A Computationally Efficient Framework for Vector Representation of Persistence Diagrams · JMLR · 2022 · 在第 37 页
- A Closer Look at Embedding Propagation for Manifold Smoothing · JMLR · 2022 · 在第 37 页
- A Class of Conjugate Priors for Multinomial Probit Models which Includes the Multivariate Normal One · JMLR · 2022 · 在第 37 页
- A Bregman Learning Framework for Sparse Neural Networks · JMLR · 2022 · 在第 37 页
- (f,Gamma)-Divergences: Interpolating between f-Divergences and Integral Probability Metrics · JMLR · 2022 · 在第 37 页