{"total":41,"rows":[{"id":"2105.02180","title":"A unifying tutorial on Approximate Message Passing","created":"2021-05-05","cited_by_count":50,"area":null},{"id":"2310.07891","title":"A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks","created":"2023-10-11","cited_by_count":49,"area":null},{"id":"2104.09311","title":"Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls","created":"2021-04-19","cited_by_count":24,"area":null},{"id":"2102.02171","title":"Outlier-Robust Learning of Ising Models Under Dobrushin's Condition","created":"2021-02-03","cited_by_count":14,"area":null},{"id":"2102.07006","title":"Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections","created":"2021-02-13","cited_by_count":12,"area":null},{"id":"2211.03860","title":"Automatic Change-Point Detection in Time Series via Deep Learning","created":"2022-11-07","cited_by_count":12,"area":null},{"id":"2104.12232","title":"Variational Inference in high-dimensional linear regression","created":"2021-04-25","cited_by_count":10,"area":null},{"id":"2212.14562","title":"Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2301.13273","title":"Near Optimal Private and Robust Linear Regression","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2102.02450","title":"Sharper Sub-Weibull Concentrations","created":"2021-02-04","cited_by_count":8,"area":null},{"id":"2505.18346","title":"On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2105.02487","title":"High-dimensional Functional Graphical Model Structure Learning via Neighborhood Selection Approach","created":"2021-05-06","cited_by_count":7,"area":null},{"id":"2312.07142","title":"General Tail Bounds for Non-Smooth Stochastic Mirror Descent","created":"2023-12-12","cited_by_count":7,"area":null},{"id":"2201.02313","title":"Stochastic Saddle Point Problems with Decision-Dependent Distributions","created":"2022-01-07","cited_by_count":6,"area":null},{"id":"2311.08168","title":"Time-Uniform Confidence Spheres for Means of Random Vectors","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2110.02885","title":"Bayesian neural network unit priors and generalized Weibull-tail property","created":"2021-10-06","cited_by_count":5,"area":null},{"id":"2104.06667","title":"Double Robust Semi-Supervised Inference for the Mean: Selection Bias under MAR Labeling with Decaying Overlap","created":"2021-04-14","cited_by_count":4,"area":null},{"id":"2212.14511","title":"Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part I","created":"2022-12-30","cited_by_count":3,"area":null},{"id":"2404.08913","title":"On the best approximation by finite Gaussian mixtures","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2407.02827","title":"Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2112.14738","title":"Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems","created":"2021-12-29","cited_by_count":2,"area":null},{"id":"2205.13507","title":"A Framework for Overparameterized Learning","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2508.21571","title":"Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks for the Poisson Equation","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2306.10395","title":"Distributed Semi-Supervised Sparse Statistical Inference","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2307.12395","title":"Concentration inequalities for high-dimensional linear processes with dependent innovations","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2403.02873","title":"A General Reduction for High-Probability Analysis with General Light-Tailed Distributions","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2505.03649","title":"Weighted Random Dot Product Graphs","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2106.07717","title":"Robust Inference for High-Dimensional Linear Models via Residual Randomization","created":"2021-06-14","cited_by_count":0,"area":null},{"id":"2107.08686","title":"Improved Learning Rates for Stochastic Optimization","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2107.09150","title":"Inference for Change Points in High Dimensional Mean Shift Models","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2304.11958","title":"Estimation of sparse linear regression coefficients under $L$-subexponential covariates","created":"2023-04-24","cited_by_count":0,"area":null},{"id":"2407.11386","title":"Exponential tilting of subweibull distributions","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2410.06326","title":"Convex Estimation of Gaussian Graphical Regression Models with Covariates","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2605.17767","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.13287","title":"Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.03596","title":"Empirical Bayes for correlated Gaussian sequence model","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.15466","title":"High-Dimensional Nonparametric Change-Point Detection via Low-Rank Degree-Three Density Projection","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.03504","title":"Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.32195","title":"High-Probability Guarantees for SGD under $\\beta$-Heavy-Tailed Gradient Noise","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33675","title":"Benign Overfitting for General Norms and Distributions","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37917","title":"Search Dimension in Unlabeled Projection Pursuit: A Scaling Law for Subspace Restriction","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}