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
2023 年 · JMLR
Journal of Machine Learning Research,2023 年发表的 400 篇,新的在前。点标题看作者和摘要。回到 2023 年
- skrl: Modular and Flexible Library for Reinforcement Learning · JMLR · 2023 · 在第 27 页
- q-Learning in Continuous Time · JMLR · 2023 · 在第 27 页
- Zeroth-Order Alternating Gradient Descent Ascent Algorithms for A Class of Nonconvex-Nonconcave Minimax Problems · JMLR · 2023 · 在第 27 页
- Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule · JMLR · 2023 · 在第 27 页
- When Locally Linear Embedding Hits Boundary · JMLR · 2023 · 在第 27 页
- Weisfeiler and Leman go Machine Learning: The Story so far · JMLR · 2023 · 在第 27 页
- Weibull Racing Survival Analysis with Competing Events, Left Truncation, and Time-Varying Covariates · JMLR · 2023 · 在第 27 页
- Variational Inverting Network for Statistical Inverse Problems of Partial Differential Equations · JMLR · 2023 · 在第 27 页
- Variational Inference for Deblending Crowded Starfields · JMLR · 2023 · 在第 27 页
- Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data · JMLR · 2023 · 在第 27 页
- VCG Mechanism Design with Unknown Agent Values under Stochastic Bandit Feedback · JMLR · 2023 · 在第 27 页
- Universal Approximation Property of Invertible Neural Networks · JMLR · 2023 · 在第 27 页
- Unbiased Multilevel Monte Carlo Methods for Intractable Distributions: MLMC Meets MCMC · JMLR · 2023 · 在第 27 页
- Two Sample Testing in High Dimension via Maximum Mean Discrepancy · JMLR · 2023 · 在第 27 页
- Tree-AMP: Compositional Inference with Tree Approximate Message Passing · JMLR · 2023 · 在第 27 页
- Tractable and Near-Optimal Adversarial Algorithms for Robust Estimation in Contaminated Gaussian Models · JMLR · 2023 · 在第 27 页
- Towards Learning to Imitate from a Single Video Demonstration · JMLR · 2023 · 在第 27 页
- Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architectures · JMLR · 2023 · 在第 27 页
- TorchOpt: An Efficient Library for Differentiable Optimization · JMLR · 2023 · 在第 27 页
- Topological Hidden Markov Models · JMLR · 2023 · 在第 27 页
- Topological Convolutional Layers for Deep Learning · JMLR · 2023 · 在第 27 页
- The multimarginal optimal transport formulation of adversarial multiclass classification · JMLR · 2023 · 在第 27 页
- The d-Separation Criterion in Categorical Probability · JMLR · 2023 · 在第 27 页
- The SKIM-FA Kernel: High-Dimensional Variable Selection and Nonlinear Interaction Discovery in Linear Time · JMLR · 2023 · 在第 27 页
- The Proximal ID Algorithm · JMLR · 2023 · 在第 27 页
- The Power of Contrast for Feature Learning: A Theoretical Analysis · JMLR · 2023 · 在第 27 页
- The Measure and Mismeasure of Fairness · JMLR · 2023 · 在第 27 页
- The Implicit Bias of Benign Overfitting · JMLR · 2023 · 在第 27 页
- The Hyperspherical Geometry of Community Detection: Modularity as a Distance · JMLR · 2023 · 在第 27 页
- The Geometry and Calculus of Losses · JMLR · 2023 · 在第 28 页
- The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima · JMLR · 2023 · 在第 28 页
- The Brier Score under Administrative Censoring: Problems and a Solution · JMLR · 2023 · 在第 28 页
- The Bayesian Learning Rule · JMLR · 2023 · 在第 28 页
- The Art of BART: Minimax Optimality over Nonhomogeneous Smoothness in High Dimension · JMLR · 2023 · 在第 28 页
- Temporal Abstraction in Reinforcement Learning with the Successor Representation · JMLR · 2023 · 在第 28 页
- T-Cal: An Optimal Test for the Calibration of Predictive Models · JMLR · 2023 · 在第 28 页
- Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Prediction · JMLR · 2023 · 在第 28 页
- Strategic Knowledge Transfer · JMLR · 2023 · 在第 28 页
- Stochastic Optimization under Distributional Drift · JMLR · 2023 · 在第 28 页
- Statistical Robustness of Empirical Risks in Machine Learning · JMLR · 2023 · 在第 28 页
- Statistical Inference for Noisy Incomplete Binary Matrix · JMLR · 2023 · 在第 28 页
- Statistical Comparisons of Classifiers by Generalized Stochastic Dominance · JMLR · 2023 · 在第 28 页
- Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint · JMLR · 2023 · 在第 28 页
- Sparse Plus Low Rank Matrix Decomposition: A Discrete Optimization Approach · JMLR · 2023 · 在第 28 页
- Sparse PCA: a Geometric Approach · JMLR · 2023 · 在第 28 页
- Sparse Markov Models for High-dimensional Inference · JMLR · 2023 · 在第 28 页
- Sparse Graph Learning from Spatiotemporal Time Series · JMLR · 2023 · 在第 28 页
- Sparse GCA and Thresholded Gradient Descent · JMLR · 2023 · 在第 28 页
- Small Transformers Compute Universal Metric Embeddings · JMLR · 2023 · 在第 28 页
- Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees · JMLR · 2023 · 在第 28 页
- Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation · JMLR · 2023 · 在第 28 页
- Set-valued Classification with Out-of-distribution Detection for Many Classes · JMLR · 2023 · 在第 28 页
- Sensitivity-Free Gradient Descent Algorithms · JMLR · 2023 · 在第 28 页
- Sensing Theorems for Unsupervised Learning in Linear Inverse Problems · JMLR · 2023 · 在第 28 页
- Semiparametric Inference Using Fractional Posteriors · JMLR · 2023 · 在第 28 页
- Semi-Supervised Off-Policy Reinforcement Learning and Value Estimation for Dynamic Treatment Regimes · JMLR · 2023 · 在第 28 页
- Selective inference for k-means clustering · JMLR · 2023 · 在第 28 页
- Selection by Prediction with Conformal p-values · JMLR · 2023 · 在第 28 页
- Scaling Up Models and Data with t5x and seqio · JMLR · 2023 · 在第 28 页
- Scale Invariant Power Iteration · JMLR · 2023 · 在第 29 页
- Scalable high-dimensional Bayesian varying coefficient models with unknown within-subject covariance · JMLR · 2023 · 在第 29 页
- Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks · JMLR · 2023 · 在第 29 页
- Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice · JMLR · 2023 · 在第 29 页
- Scalable Computation of Causal Bounds · JMLR · 2023 · 在第 29 页
- Sampling random graph homomorphisms and applications to network data analysis · JMLR · 2023 · 在第 29 页
- Sample Complexity for Distributionally Robust Learning under chi-square divergence · JMLR · 2023 · 在第 29 页
- SQLFlow: An Extensible Toolkit Integrating DB and AI · JMLR · 2023 · 在第 29 页
- Robust Methods for High-Dimensional Linear Learning · JMLR · 2023 · 在第 29 页
- Robust Load Balancing with Machine Learned Advice · JMLR · 2023 · 在第 29 页
- Robust High-Dimensional Low-Rank Matrix Estimation: Optimal Rate and Data-Adaptive Tuning · JMLR · 2023 · 在第 29 页
- Risk Bounds for Positive-Unlabeled Learning Under the Selected At Random Assumption · JMLR · 2023 · 在第 29 页
- Ridges, Neural Networks, and the Radon Transform · JMLR · 2023 · 在第 29 页
- Revisiting minimum description length complexity in overparameterized models · JMLR · 2023 · 在第 29 页
- Revisiting inference after prediction · JMLR · 2023 · 在第 29 页
- Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the in the O(epsilon^(-7/4)) Complexity · JMLR · 2023 · 在第 29 页
- Reproducing Kernels and New Approaches in Compositional Data Analysis · JMLR · 2023 · 在第 29 页
- Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD · JMLR · 2023 · 在第 29 页
- Reinforcement Learning for Joint Optimization of Multiple Rewards · JMLR · 2023 · 在第 29 页
- Regularized Joint Mixture Models · JMLR · 2023 · 在第 29 页
- Recursive Quantile Estimation: Non-Asymptotic Confidence Bounds · JMLR · 2023 · 在第 29 页
- RankSEG: A Consistent Ranking-based Framework for Segmentation · JMLR · 2023 · 在第 29 页
- Randomized Spectral Co-Clustering for Large-Scale Directed Networks · JMLR · 2023 · 在第 29 页
- Random Forests for Change Point Detection · JMLR · 2023 · 在第 29 页
- Random Feature Neural Networks Learn Black-Scholes Type PDEs Without Curse of Dimensionality · JMLR · 2023 · 在第 29 页
- Random Feature Amplification: Feature Learning and Generalization in Neural Networks · JMLR · 2023 · 在第 29 页
- Radial Basis Approximation of Tensor Fields on Manifolds: From Operator Estimation to Manifold Learning · JMLR · 2023 · 在第 29 页
- RVCL: Evaluating the Robustness of Contrastive Learning via Verification · JMLR · 2023 · 在第 29 页
- Quasi-Equivalence between Width and Depth of Neural Networks · JMLR · 2023 · 在第 29 页
- Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond · JMLR · 2023 · 在第 29 页
- Quantifying Network Similarity using Graph Cumulants · JMLR · 2023 · 在第 29 页
- Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity · JMLR · 2023 · 在第 29 页
- Python package for causal discovery based on LiNGAM · JMLR · 2023 · 在第 29 页
- Provably Sample-Efficient Model-Free Algorithm for MDPs with Peak Constraints · JMLR · 2023 · 在第 29 页
- ProtoryNet - Interpretable Text Classification Via Prototype Trajectories · JMLR · 2023 · 在第 29 页
- ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI · JMLR · 2023 · 在第 30 页
- Privacy-Aware Rejection Sampling · JMLR · 2023 · 在第 30 页
- Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching · JMLR · 2023 · 在第 30 页
- Principled Out-of-Distribution Detection via Multiple Testing · JMLR · 2023 · 在第 30 页
- Prediction Equilibrium for Dynamic Network Flows · JMLR · 2023 · 在第 30 页
- Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification · JMLR · 2023 · 在第 30 页
- Posterior Contraction for Deep Gaussian Process Priors · JMLR · 2023 · 在第 30 页
- Posterior Consistency for Bayesian Relevance Vector Machines · JMLR · 2023 · 在第 30 页
- Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications · JMLR · 2023 · 在第 30 页
- Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games · JMLR · 2023 · 在第 30 页
- Pivotal Estimation of Linear Discriminant Analysis in High Dimensions · JMLR · 2023 · 在第 30 页
- Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set · JMLR · 2023 · 在第 30 页
- PaLM: Scaling Language Modeling with Pathways · JMLR · 2023 · 在第 30 页
- PAC-learning for Strategic Classification · JMLR · 2023 · 在第 30 页
- Over-parameterized Deep Nonparametric Regression for Dependent Data with Its Applications to Reinforcement Learning · JMLR · 2023 · 在第 30 页
- Outlier-Robust Subsampling Techniques for Persistent Homology · JMLR · 2023 · 在第 30 页
- Optimizing ROC Curves with a Sort-Based Surrogate Loss for Binary Classification and Changepoint Detection · JMLR · 2023 · 在第 30 页
- Optimal Strategies for Reject Option Classifiers · JMLR · 2023 · 在第 30 页
- Optimal Parameter-Transfer Learning by Semiparametric Model Averaging · JMLR · 2023 · 在第 30 页
- Optimal Convergence Rates for Distributed Nystroem Approximation · JMLR · 2023 · 在第 30 页
- Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces · JMLR · 2023 · 在第 30 页
- Operator learning with PCA-Net: upper and lower complexity bounds · JMLR · 2023 · 在第 30 页
- Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval · JMLR · 2023 · 在第 30 页
- Online Optimization over Riemannian Manifolds · JMLR · 2023 · 在第 30 页
- Online Non-stochastic Control with Partial Feedback · JMLR · 2023 · 在第 30 页
- Online Change-Point Detection in High-Dimensional Covariance Structure with Application to Dynamic Networks · JMLR · 2023 · 在第 30 页
- On the geometry of Stein variational gradient descent · JMLR · 2023 · 在第 30 页
- On the Theoretical Equivalence of Several Trade-Off Curves Assessing Statistical Proximity · JMLR · 2023 · 在第 30 页
- On the Optimality of Nuclear-norm-based Matrix Completion for Problems with Smooth Non-linear Structure · JMLR · 2023 · 在第 30 页
- On the Estimation of Derivatives Using Plug-in Kernel Ridge Regression Estimators · JMLR · 2023 · 在第 30 页
- On the Dynamics Under the Unhinged Loss and Beyond · JMLR · 2023 · 在第 30 页
- On the Convergence of Stochastic Gradient Descent with Bandwidth-based Step Size · JMLR · 2023 · 在第 30 页
- On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results · JMLR · 2023 · 在第 30 页
- On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error · JMLR · 2023 · 在第 30 页
- On Tilted Losses in Machine Learning: Theory and Applications · JMLR · 2023 · 在第 31 页
- On Learning Rates and Schrödinger Operators · JMLR · 2023 · 在第 31 页
- On Distance and Kernel Measures of Conditional Dependence · JMLR · 2023 · 在第 31 页
- On Biased Compression for Distributed Learning · JMLR · 2023 · 在第 31 页
- On Batch Teaching Without Collusion · JMLR · 2023 · 在第 31 页
- Off-Policy Actor-Critic with Emphatic Weightings · JMLR · 2023 · 在第 31 页
- Non-stationary Online Learning with Memory and Non-stochastic Control · JMLR · 2023 · 在第 31 页
- Non-Asymptotic Guarantees for Robust Statistical Learning under Infinite Variance Assumption · JMLR · 2023 · 在第 31 页
- Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research · JMLR · 2023 · 在第 31 页
- Neural Q-learning for solving PDEs · JMLR · 2023 · 在第 31 页
- Neural Operator: Learning Maps Between Function Spaces With Applications to PDEs · JMLR · 2023 · 在第 31 页
- Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data · JMLR · 2023 · 在第 31 页
- Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problems · JMLR · 2023 · 在第 31 页
- Nearest Neighbor Dirichlet Mixtures · JMLR · 2023 · 在第 31 页
- Near-Optimal Weighted Matrix Completion · JMLR · 2023 · 在第 31 页
- Naive regression requires weaker assumptions than factor models to adjust for multiple cause confounding · JMLR · 2023 · 在第 31 页
- Multivariate Soft Rank via Entropy-Regularized Optimal Transport: Sample Efficiency and Generative Modeling · JMLR · 2023 · 在第 31 页
- Multiplayer Performative Prediction: Learning in Decision-Dependent Games · JMLR · 2023 · 在第 31 页
- Multilevel CNNs for Parametric PDEs · JMLR · 2023 · 在第 31 页
- MultiZoo and MultiBench: A Standardized Toolkit for Multimodal Deep Learning · JMLR · 2023 · 在第 31 页
- Multi-view Collaborative Gaussian Process Dynamical Systems · JMLR · 2023 · 在第 31 页
- Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices · JMLR · 2023 · 在第 31 页
- Multi-Consensus Decentralized Accelerated Gradient Descent · JMLR · 2023 · 在第 31 页
- Monotonic Alpha-divergence Minimisation for Variational Inference · JMLR · 2023 · 在第 31 页
- Modular Regression: Improving Linear Models by Incorporating Auxiliary Data · JMLR · 2023 · 在第 31 页
- Model-based Causal Discovery for Zero-Inflated Count Data · JMLR · 2023 · 在第 31 页
- Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity · JMLR · 2023 · 在第 31 页
- Mixed Regression via Approximate Message Passing · JMLR · 2023 · 在第 31 页
- Minimax Risk Classifiers with 0-1 Loss · JMLR · 2023 · 在第 31 页
- Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training? · JMLR · 2023 · 在第 31 页
- Minimal Width for Universal Property of Deep RNN · JMLR · 2023 · 在第 31 页
- Mini-batching error and adaptive Langevin dynamics · JMLR · 2023 · 在第 32 页
- Microcanonical Hamiltonian Monte Carlo · JMLR · 2023 · 在第 32 页
- Metrizing Weak Convergence with Maximum Mean Discrepancies · JMLR · 2023 · 在第 32 页
- Merlion: End-to-End Machine Learning for Time Series · JMLR · 2023 · 在第 32 页
- Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning · JMLR · 2023 · 在第 32 页
- Maximum likelihood estimation in Gaussian process regression is ill-posed · JMLR · 2023 · 在第 32 页
- MMD Aggregated Two-Sample Test · JMLR · 2023 · 在第 32 页
- MAUVE Scores for Generative Models: Theory and Practice · JMLR · 2023 · 在第 32 页
- MARS: A Second-Order Reduction Algorithm for High-Dimensional Sparse Precision Matrices Estimation · JMLR · 2023 · 在第 32 页
- MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library · JMLR · 2023 · 在第 32 页
- MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning · JMLR · 2023 · 在第 32 页
- Lower Bounds and Accelerated Algorithms for Bilevel Optimization · JMLR · 2023 · 在第 32 页
- Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence · JMLR · 2023 · 在第 32 页
- Low Tree-Rank Bayesian Vector Autoregression Models · JMLR · 2023 · 在第 32 页
- Linear Partial Monitoring for Sequential Decision Making: Algorithms, Regret Bounds and Applications · JMLR · 2023 · 在第 32 页
- Limits of Dense Simplicial Complexes · JMLR · 2023 · 在第 32 页
- Limitations on approximation by deep and shallow neural networks · JMLR · 2023 · 在第 32 页
- Lifted Bregman Training of Neural Networks · JMLR · 2023 · 在第 32 页
- LibMTL: A Python Library for Deep Multi-Task Learning · JMLR · 2023 · 在第 32 页
- Least Squares Model Averaging for Distributed Data · JMLR · 2023 · 在第 32 页
- Learning-augmented count-min sketches via Bayesian nonparametrics · JMLR · 2023 · 在第 32 页
- Learning to Rank under Multinomial Logit Choice · JMLR · 2023 · 在第 32 页
- Learning an Explicit Hyper-parameter Prediction Function Conditioned on Tasks · JMLR · 2023 · 在第 32 页
- Learning Partial Differential Equations in Reproducing Kernel Hilbert Spaces · JMLR · 2023 · 在第 32 页
- Learning Optimal Group-structured Individualized Treatment Rules with Many Treatments · JMLR · 2023 · 在第 32 页
- Learning Optimal Feedback Operators and their Sparse Polynomial Approximations · JMLR · 2023 · 在第 32 页
- Learning Mean-Field Games with Discounted and Average Costs · JMLR · 2023 · 在第 32 页
- Learning Good State and Action Representations for Markov Decision Process via Tensor Decomposition · JMLR · 2023 · 在第 32 页
- Learning Conditional Generative Models for Phase Retrieval · JMLR · 2023 · 在第 32 页
- Leaky Hockey Stick Loss: The First Negatively Divergent Margin-based Loss Function for Classification · JMLR · 2023 · 在第 32 页
- Large sample spectral analysis of graph-based multi-manifold clustering · JMLR · 2023 · 在第 32 页
- Large data limit of the MBO scheme for data clustering: convergence of the dynamics · JMLR · 2023 · 在第 32 页
- LapGym - An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery · JMLR · 2023 · 在第 32 页
- Labels, Information, and Computation: Efficient Learning Using Sufficient Labels · JMLR · 2023 · 在第 32 页
- Label Distribution Changing Learning with Sample Space Expanding · JMLR · 2023 · 在第 32 页
- L0Learn: A Scalable Package for Sparse Learning using L0 Regularization · JMLR · 2023 · 在第 32 页
- Knowledge Hypergraph Embedding Meets Relational Algebra · JMLR · 2023 · 在第 32 页
- Kernel-based estimation for partially functional linear model: Minimax rates and randomized sketches · JMLR · 2023 · 在第 32 页
- Kernel-Matrix Determinant Estimates from stopped Cholesky Decomposition · JMLR · 2023 · 在第 32 页
- Jump Interval-Learning for Individualized Decision Making with Continuous Treatments · JMLR · 2023 · 在第 32 页
- Iterated Block Particle Filter for High-dimensional Parameter Learning: Beating the Curse of Dimensionality · JMLR · 2023 · 在第 33 页
- Intrinsic Persistent Homology via Density-based Metric Learning · JMLR · 2023 · 在第 33 页
- Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics · JMLR · 2023 · 在第 33 页
- Interpretable and Fair Boolean Rule Sets via Column Generation · JMLR · 2023 · 在第 33 页
- Interpolating Classifiers Make Few Mistakes · JMLR · 2023 · 在第 33 页
- Integrating Random Effects in Deep Neural Networks · JMLR · 2023 · 在第 33 页
- Instance-Dependent Generalization Bounds via Optimal Transport · JMLR · 2023 · 在第 33 页
- Instance-Dependent Confidence and Early Stopping for Reinforcement Learning · JMLR · 2023 · 在第 33 页
- Insights into Ordinal Embedding Algorithms: A Systematic Evaluation · JMLR · 2023 · 在第 33 页
- Infinite-dimensional optimization and Bayesian nonparametric learning of stochastic differential equations · JMLR · 2023 · 在第 33 页
- Inference on the Change Point under a High Dimensional Covariance Shift · JMLR · 2023 · 在第 33 页
- Inference for a Large Directed Acyclic Graph with Unspecified Interventions · JMLR · 2023 · 在第 33 页
- Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds · JMLR · 2023 · 在第 33 页
- Incremental Learning in Diagonal Linear Networks · JMLR · 2023 · 在第 33 页
- Improving multiple-try Metropolis with local balancing · JMLR · 2023 · 在第 33 页
- Improved Powered Stochastic Optimization Algorithms for Large-Scale Machine Learning · JMLR · 2023 · 在第 33 页
- Importance Sparsification for Sinkhorn Algorithm · JMLR · 2023 · 在第 33 页
- Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion · JMLR · 2023 · 在第 33 页
- Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks · JMLR · 2023 · 在第 33 页
- Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping · JMLR · 2023 · 在第 33 页
- How Do You Want Your Greedy: Simultaneous or Repeated? · JMLR · 2023 · 在第 33 页
- Higher-Order Spectral Clustering Under Superimposed Stochastic Block Models · JMLR · 2023 · 在第 33 页
- High-Dimensional Inference for Generalized Linear Models with Hidden Confounding · JMLR · 2023 · 在第 33 页
- Hierarchical Kernels in Deep Kernel Learning · JMLR · 2023 · 在第 33 页
- HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation · JMLR · 2023 · 在第 33 页
- HiClass: a Python Library for Local Hierarchical Classification Compatible with Scikit-learn · JMLR · 2023 · 在第 33 页
- Hard-Constrained Deep Learning for Climate Downscaling · JMLR · 2023 · 在第 33 页
- Group SLOPE Penalized Low-Rank Tensor Regression · JMLR · 2023 · 在第 33 页
- Graph-Aided Online Multi-Kernel Learning · JMLR · 2023 · 在第 33 页
- Graph Clustering with Graph Neural Networks · JMLR · 2023 · 在第 33 页
- Graph Attention Retrospective · JMLR · 2023 · 在第 33 页
- Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation · JMLR · 2023 · 在第 33 页
- Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization · JMLR · 2023 · 在第 34 页
- Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables · JMLR · 2023 · 在第 34 页
- Generalized Linear Models in Non-interactive Local Differential Privacy with Public Data · JMLR · 2023 · 在第 34 页
- Generalization error bounds for multiclass sparse linear classifiers · JMLR · 2023 · 在第 34 页
- Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels · JMLR · 2023 · 在第 34 页
- Generalization Bounds for Adversarial Contrastive Learning · JMLR · 2023 · 在第 34 页
- Gaussian Processes with Errors in Variables: Theory and Computation · JMLR · 2023 · 在第 34 页
- Gap Minimization for Knowledge Sharing and Transfer · JMLR · 2023 · 在第 34 页
- GFlowNet Foundations · JMLR · 2023 · 在第 34 页
- GANs as Gradient Flows that Converge · JMLR · 2023 · 在第 34 页
- Fundamental limits and algorithms for sparse linear regression with sublinear sparsity · JMLR · 2023 · 在第 34 页
- Functional L-Optimality Subsampling for Functional Generalized Linear Models with Massive Data · JMLR · 2023 · 在第 34 页
- From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms · JMLR · 2023 · 在第 34 页
- From Classification Accuracy to Proper Scoring Rules: Elicitability of Probabilistic Top List Predictions · JMLR · 2023 · 在第 34 页
- Fourier Neural Operator with Learned Deformations for PDEs on General Geometries · JMLR · 2023 · 在第 34 页
- Foundation Models and Fair Use · JMLR · 2023 · 在第 34 页
- Flexible Model Aggregation for Quantile Regression · JMLR · 2023 · 在第 34 页
- Fitting Autoregressive Graph Generative Models through Maximum Likelihood Estimation · JMLR · 2023 · 在第 34 页
- First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems · JMLR · 2023 · 在第 34 页
- Finite-time Koopman Identifier: A Unified Batch-online Learning Framework for Joint Learning of Koopman Structure and Parameters · JMLR · 2023 · 在第 34 页
- Finding Groups of Cross-Correlated Features in Bi-View Data · JMLR · 2023 · 在第 34 页
- FedLab: A Flexible Federated Learning Framework · JMLR · 2023 · 在第 34 页
- Fast Screening Rules for Optimal Design via Quadratic Lasso Reformulation · JMLR · 2023 · 在第 34 页
- Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics · JMLR · 2023 · 在第 34 页
- Fast Objective & Duality Gap Convergence for Non-Convex Strongly-Concave Min-Max Problems with PL Condition · JMLR · 2023 · 在第 34 页
- Fast Expectation Propagation for Heteroscedastic, Lasso-Penalized, and Quantile Regression · JMLR · 2023 · 在第 34 页
- Faith-Shap: The Faithful Shapley Interaction Index · JMLR · 2023 · 在第 34 页
- Fairlearn: Assessing and Improving Fairness of AI Systems · JMLR · 2023 · 在第 34 页
- Fair Data Representation for Machine Learning at the Pareto Frontier · JMLR · 2023 · 在第 34 页
- Factor Graph Neural Networks · JMLR · 2023 · 在第 34 页
- FLIP: A Utility Preserving Privacy Mechanism for Time Series · JMLR · 2023 · 在第 34 页
- F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning · JMLR · 2023 · 在第 34 页
- Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions · JMLR · 2023 · 在第 34 页
- Exploiting Discovered Regression Discontinuities to Debias Conditioned-on-observable Estimators · JMLR · 2023 · 在第 34 页
- Evaluating Instrument Validity using the Principle of Independent Mechanisms · JMLR · 2023 · 在第 34 页
- Euler-Lagrange Analysis of Generative Adversarial Networks · JMLR · 2023 · 在第 34 页
- Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model · JMLR · 2023 · 在第 35 页
- Escaping The Curse of Dimensionality in Bayesian Model-Based Clustering · JMLR · 2023 · 在第 35 页
- Entropic Fictitious Play for Mean Field Optimization Problem · JMLR · 2023 · 在第 35 页
- Elastic Gradient Descent, an Iterative Optimization Method Approximating the Solution Paths of the Elastic Net · JMLR · 2023 · 在第 35 页
- Efficient Structure-preserving Support Tensor Train Machine · JMLR · 2023 · 在第 35 页
- Efficient Computation of Rankings from Pairwise Comparisons · JMLR · 2023 · 在第 35 页
- Dynamic Ranking with the BTL Model: A Nearest Neighbor based Rank Centrality Method · JMLR · 2023 · 在第 35 页
- Dropout Training is Distributionally Robust Optimal · JMLR · 2023 · 在第 35 页
- Doubly Robust Stein-Kernelized Monte Carlo Estimator: Simultaneous Bias-Variance Reduction and Supercanonical Convergence · JMLR · 2023 · 在第 35 页
- Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning · JMLR · 2023 · 在第 35 页
- Divide-and-Conquer Fusion · JMLR · 2023 · 在第 35 页
- Distributed Statistical Inference under Heterogeneity · JMLR · 2023 · 在第 35 页
- Distributed Sparse Regression via Penalization · JMLR · 2023 · 在第 35 页
- Distributed Nonparametric Regression Imputation for Missing Response Problems with Large-scale Data · JMLR · 2023 · 在第 35 页
- Distributed Community Detection in Large Networks · JMLR · 2023 · 在第 35 页
- Distributed Algorithms for U-statistics-based Empirical Risk Minimization · JMLR · 2023 · 在第 35 页
- Distinguishing Cause and Effect in Bivariate Structural Causal Models: A Systematic Investigation · JMLR · 2023 · 在第 35 页
- Discrete Variational Calculus for Accelerated Optimization · JMLR · 2023 · 在第 35 页
- Discovering Salient Neurons in deep NLP models · JMLR · 2023 · 在第 35 页
- Dimensionless machine learning: Imposing exact units equivariance · JMLR · 2023 · 在第 35 页
- Dimensionality Reduction and Wasserstein Stability for Kernel Regression · JMLR · 2023 · 在第 35 页
- Dimension-Grouped Mixed Membership Models for Multivariate Categorical Data · JMLR · 2023 · 在第 35 页
- Dimension Reduction in Contextual Online Learning via Nonparametric Variable Selection · JMLR · 2023 · 在第 35 页
- Dimension Reduction and MARS · JMLR · 2023 · 在第 35 页
- Diffusion Bridge Mixture Transports, Schrödinger Bridge Problems and Generative Modeling · JMLR · 2023 · 在第 35 页
- Differentially Private Hypothesis Testing for Linear Regression · JMLR · 2023 · 在第 35 页
- Density estimation on low-dimensional manifolds: an inflation-deflation approach · JMLR · 2023 · 在第 35 页
- Densely Connected G-invariant Deep Neural Networks with Signed Permutation Representations · JMLR · 2023 · 在第 35 页
- Deletion and Insertion Tests in Regression Models · JMLR · 2023 · 在第 35 页
- Deep linear networks can benignly overfit when shallow ones do · JMLR · 2023 · 在第 35 页
- Deep Neural Networks with Dependent Weights: Gaussian Process Mixture Limit, Heavy Tails, Sparsity and Compressibility · JMLR · 2023 · 在第 35 页
- Decentralized Robust V-learning for Solving Markov Games with Model Uncertainty · JMLR · 2023 · 在第 35 页
- Decentralized Learning: Theoretical Optimality and Practical Improvements · JMLR · 2023 · 在第 35 页
- DART: Distance Assisted Recursive Testing · JMLR · 2023 · 在第 35 页
- Convex Reinforcement Learning in Finite Trials · JMLR · 2023 · 在第 36 页
- Convergence Rates of a Class of Multivariate Density Estimation Methods Based on Adaptive Partitioning · JMLR · 2023 · 在第 36 页
- Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning · JMLR · 2023 · 在第 36 页
- Contrasting Identifying Assumptions of Average Causal Effects: Robustness and Semiparametric Efficiency · JMLR · 2023 · 在第 36 页
- Continuous-in-time Limit for Bayesian Bandits · JMLR · 2023 · 在第 36 页
- Contextual Stochastic Block Model: Sharp Thresholds and Contiguity · JMLR · 2023 · 在第 36 页
- Consistent Second-Order Conic Integer Programming for Learning Bayesian Networks · JMLR · 2023 · 在第 36 页
- Consistent Model-based Clustering using the Quasi-Bernoulli Stick-breaking Process · JMLR · 2023 · 在第 36 页
- Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity · JMLR · 2023 · 在第 36 页
- Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queries · JMLR · 2023 · 在第 36 页
- Confidence and Uncertainty Assessment for Distributional Random Forests · JMLR · 2023 · 在第 36 页
- Confidence Intervals and Hypothesis Testing for High-dimensional Quantile Regression: Convolution Smoothing and Debiasing · JMLR · 2023 · 在第 36 页
- Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data · JMLR · 2023 · 在第 36 页
- Concentration analysis of multivariate elliptic diffusions · JMLR · 2023 · 在第 36 页
- Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities · JMLR · 2023 · 在第 36 页
- Compression, Generalization and Learning · JMLR · 2023 · 在第 36 页
- Comprehensive Algorithm Portfolio Evaluation using Item Response Theory · JMLR · 2023 · 在第 36 页
- Community models for networks observed through edge nominations · JMLR · 2023 · 在第 36 页
- Community Recovery in the Geometric Block Model · JMLR · 2023 · 在第 36 页
- Combinatorial Optimization and Reasoning with Graph Neural Networks · JMLR · 2023 · 在第 36 页
- CodaLab Competitions: An Open Source Platform to Organize Scientific Challenges · JMLR · 2023 · 在第 36 页
- Clustering with Tangles: Algorithmic Framework and Theoretical Guarantees · JMLR · 2023 · 在第 36 页
- Clustering and Structural Robustness in Causal Diagrams · JMLR · 2023 · 在第 36 页
- Cluster-Specific Predictions with Multi-Task Gaussian Processes · JMLR · 2023 · 在第 36 页
- Causal Discovery with Unobserved Confounding and Non-Gaussian Data · JMLR · 2023 · 在第 36 页
- Causal Bandits for Linear Structural Equation Models · JMLR · 2023 · 在第 36 页
- Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopically Rational Followers? · JMLR · 2023 · 在第 36 页
- Calibrated Multiple-Output Quantile Regression with Representation Learning · JMLR · 2023 · 在第 36 页
- Buffered Asynchronous SGD for Byzantine Learning · JMLR · 2023 · 在第 36 页
- Boosting Multi-agent Reinforcement Learning via Contextual Prompting · JMLR · 2023 · 在第 36 页
- Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start · JMLR · 2023 · 在第 36 页
- Beyond the Golden Ratio for Variational Inequality Algorithms · JMLR · 2023 · 在第 36 页
- Beyond Spectral Gap: The Role of the Topology in Decentralized Learning · JMLR · 2023 · 在第 36 页
- Benign overfitting in ridge regression · JMLR · 2023 · 在第 36 页
- Benign Overfitting of Constant-Stepsize SGD for Linear Regression · JMLR · 2023 · 在第 36 页
- Benchmarking Graph Neural Networks · JMLR · 2023 · 在第 37 页
- Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders · JMLR · 2023 · 在第 37 页
- Bayesian Spiked Laplacian Graphs · JMLR · 2023 · 在第 37 页
- Bayesian Spanning Tree: Estimating the Backbone of the Dependence Graph · JMLR · 2023 · 在第 37 页
- Bayesian Data Selection · JMLR · 2023 · 在第 37 页
- Bayesian Calibration of Imperfect Computer Models using Physics-Informed Priors · JMLR · 2023 · 在第 37 页
- Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees · JMLR · 2023 · 在第 37 页
- Bandit problems with fidelity rewards · JMLR · 2023 · 在第 37 页
- Bagging in overparameterized learning: Risk characterization and risk monotonization · JMLR · 2023 · 在第 37 页
- Avalanche: A PyTorch Library for Deep Continual Learning · JMLR · 2023 · 在第 37 页
- Autoregressive Networks · JMLR · 2023 · 在第 37 页
- AutoKeras: An AutoML Library for Deep Learning · JMLR · 2023 · 在第 37 页
- Augmented Transfer Regression Learning with Semi-non-parametric Nuisance Models · JMLR · 2023 · 在第 37 页
- Augmented Sparsifiers for Generalized Hypergraph Cuts · JMLR · 2023 · 在第 37 页
- Attribution-based Explanations that Provide Recourse Cannot be Robust · JMLR · 2023 · 在第 37 页
- Attacks against Federated Learning Defense Systems and their Mitigation · JMLR · 2023 · 在第 37 页
- Atlas: Few-shot Learning with Retrieval Augmented Language Models · JMLR · 2023 · 在第 37 页
- Asynchronous Iterations in Optimization: New Sequence Results and Sharper Algorithmic Guarantees · JMLR · 2023 · 在第 37 页
- Asymptotics of Network Embeddings Learned via Subsampling · JMLR · 2023 · 在第 37 页
- Approximation Bounds for Hierarchical Clustering: Average Linkage, Bisecting K-means, and Local Search · JMLR · 2023 · 在第 37 页
- Approximate Post-Selective Inference for Regression with the Group LASSO · JMLR · 2023 · 在第 37 页
- An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity · JMLR · 2023 · 在第 37 页
- An Inertial Block Majorization Minimization Framework for Nonsmooth Nonconvex Optimization · JMLR · 2023 · 在第 37 页
- An Empirical Investigation of the Role of Pre-training in Lifelong Learning · JMLR · 2023 · 在第 37 页
- An Eigenmodel for Dynamic Multilayer Networks · JMLR · 2023 · 在第 37 页
- An Annotated Graph Model with Differential Degree Heterogeneity for Directed Networks · JMLR · 2023 · 在第 37 页
- An Analysis of Robustness of Non-Lipschitz Networks · JMLR · 2023 · 在第 37 页
- Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics · JMLR · 2023 · 在第 37 页
- Adaptive Learning of Density Ratios in RKHS · JMLR · 2023 · 在第 37 页
- Adaptive False Discovery Rate Control with Privacy Guarantee · JMLR · 2023 · 在第 37 页
- Adaptive Data Depth via Multi-Armed Bandits · JMLR · 2023 · 在第 37 页
- Adaptive Clustering Using Kernel Density Estimators · JMLR · 2023 · 在第 37 页
- Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees · JMLR · 2023 · 在第 37 页
- Adaptation to the Range in K-Armed Bandits · JMLR · 2023 · 在第 37 页
- Adaptation Augmented Model-based Policy Optimization · JMLR · 2023 · 在第 37 页
- Accelerated Primal-Dual Mirror Dynamics for Centralized and Distributed Constrained Convex Optimization Problems · JMLR · 2023 · 在第 37 页
- A Unified Theory of Diversity in Ensemble Learning · JMLR · 2023 · 在第 37 页
- A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds · JMLR · 2023 · 在第 37 页
- A Unified Framework for Optimization-Based Graph Coarsening · JMLR · 2023 · 在第 38 页
- A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning · JMLR · 2023 · 在第 38 页
- A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models · JMLR · 2023 · 在第 38 页
- A Unified Approach to Controlling Implicit Regularization via Mirror Descent · JMLR · 2023 · 在第 38 页
- A Unified Analysis of Multi-task Functional Linear Regression Models with Manifold Constraint and Composite Quadratic Penalty · JMLR · 2023 · 在第 38 页
- A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness · JMLR · 2023 · 在第 38 页
- A Scalable and Efficient Iterative Method for Copying Machine Learning Classifiers · JMLR · 2023 · 在第 38 页
- A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition · JMLR · 2023 · 在第 38 页
- A Relaxed Inertial Forward-Backward-Forward Algorithm for Solving Monotone Inclusions with Application to GANs · JMLR · 2023 · 在第 38 页
- A Randomized Subspace-based Approach for Dimensionality Reduction and Important Variable Selection · JMLR · 2023 · 在第 38 页
- A Permutation-Free Kernel Independence Test · JMLR · 2023 · 在第 38 页
- A Parameter-Free Conditional Gradient Method for Composite Minimization under Hölder Condition · JMLR · 2023 · 在第 38 页
- A PDE approach for regret bounds under partial monitoring · JMLR · 2023 · 在第 38 页
- A Novel Integer Linear Programming Approach for Global L0 Minimization · JMLR · 2023 · 在第 38 页
- A Non-parametric View of FedAvg and FedProx:Beyond Stationary Points · JMLR · 2023 · 在第 38 页
- A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits · JMLR · 2023 · 在第 38 页
- A Line-Search Descent Algorithm for Strict Saddle Functions with Complexity Guarantees · JMLR · 2023 · 在第 38 页
- A Likelihood Approach to Nonparametric Estimation of a Singular Distribution Using Deep Generative Models · JMLR · 2023 · 在第 38 页
- A Group-Theoretic Approach to Computational Abstraction: Symmetry-Driven Hierarchical Clustering · JMLR · 2023 · 在第 38 页
- A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates · JMLR · 2023 · 在第 38 页
- A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning · JMLR · 2023 · 在第 38 页
- A Framework and Benchmark for Deep Batch Active Learning for Regression · JMLR · 2023 · 在第 38 页
- A First Look into the Carbon Footprint of Federated Learning · JMLR · 2023 · 在第 38 页
- A Continuous-time Stochastic Gradient Descent Method for Continuous Data · JMLR · 2023 · 在第 38 页
- A Complete Characterization of Linear Estimators for Offline Policy Evaluation · JMLR · 2023 · 在第 38 页
- A Bayesian Bradley-Terry model to compare multiple ML algorithms on multiple data sets · JMLR · 2023 · 在第 38 页