{"total":68,"rows":[{"id":"2102.10346","title":"Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance","created":"2021-02-20","cited_by_count":35,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2106.03156","title":"Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling","created":"2021-06-06","cited_by_count":28,"area":null},{"id":"2106.01257","title":"Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize","created":"2021-06-02","cited_by_count":27,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26,"area":null},{"id":"2302.07690","title":"Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data","created":"2023-02-15","cited_by_count":20,"area":null},{"id":"2405.16644","title":"Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2201.08518","title":"Optimal variance-reduced stochastic approximation in Banach spaces","created":"2022-01-21","cited_by_count":17,"area":null},{"id":"2209.11964","title":"Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning","created":"2022-09-24","cited_by_count":15,"area":null},{"id":"2102.03389","title":"Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods","created":"2021-02-05","cited_by_count":14,"area":null},{"id":"2402.13531","title":"Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation","created":"2024-02-21","cited_by_count":12,"area":null},{"id":"2103.02860","title":"Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference","created":"2021-03-04","cited_by_count":11,"area":null},{"id":"2106.14857","title":"Bootstrapping the error of Oja's algorithm","created":"2021-06-28","cited_by_count":11,"area":null},{"id":"2205.13687","title":"Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2401.09346","title":"High Confidence Level Inference is Almost Free using Parallel Stochastic Optimization","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2502.06719","title":"Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2305.17665","title":"Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality","created":"2023-05-28","cited_by_count":9,"area":null},{"id":"2212.14883","title":"Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent","created":"2022-12-30","cited_by_count":8,"area":null},{"id":"2307.06915","title":"Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality","created":"2023-07-13","cited_by_count":8,"area":null},{"id":"2211.10837","title":"Non-reversible Parallel Tempering for Deep Posterior Approximation","created":"2022-11-20","cited_by_count":7,"area":null},{"id":"2302.12717","title":"Statistical Inference with Stochastic Gradient Methods under $\\phi$-mixing Data","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2308.01481","title":"Online covariance estimation for stochastic gradient descent under Markovian sampling","created":"2023-08-03","cited_by_count":7,"area":null},{"id":"2102.05198","title":"Statistical Inference for Polyak-Ruppert Averaged Zeroth-order Stochastic Gradient Algorithm","created":"2021-02-10","cited_by_count":6,"area":null},{"id":"2306.09686","title":"Collapsed Inference for Bayesian Deep Learning","created":"2023-06-16","cited_by_count":6,"area":null},{"id":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2212.01259","title":"Covariance Estimators for the ROOT-SGD Algorithm in Online Learning","created":"2022-12-02","cited_by_count":5,"area":null},{"id":"2312.10894","title":"Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2207.12395","title":"Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2304.13950","title":"Fairness Uncertainty Quantification: How certain are you that the model is fair?","created":"2023-04-27","cited_by_count":4,"area":null},{"id":"2310.02581","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2405.19463","title":"Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2502.05305","title":"Online Covariance Estimation in Nonsmooth Stochastic Approximation","created":"2025-02-07","cited_by_count":4,"area":null},{"id":"2510.12375","title":"Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2308.13564","title":"SGMM: Stochastic Approximation to Generalized Method of Moments","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2410.15057","title":"Asymptotic Time-Uniform Inference for Parameters in Averaged Stochastic Approximation","created":"2024-10-19","cited_by_count":3,"area":null},{"id":"2506.12655","title":"Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA","created":"2025-06-14","cited_by_count":3,"area":null},{"id":"2105.10315","title":"Online Statistical Inference for Parameters Estimation with Linear-Equality Constraints","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2109.01326","title":"Statistical Estimation and Inference via Local SGD in Federated Learning","created":"2021-09-03","cited_by_count":2,"area":null},{"id":"2109.10888","title":"A Physics inspired Functional Operator for Model Uncertainty Quantification in the RKHS","created":"2021-09-22","cited_by_count":2,"area":null},{"id":"2206.12663","title":"Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert","created":"2022-06-25","cited_by_count":2,"area":null},{"id":"2505.17300","title":"Statistical Inference for Online Algorithms","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2507.20560","title":"Statistical Inference for Differentially Private Stochastic Gradient Descent","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2509.21800","title":"Federated Learning of Quantile Inference under Local Differential Privacy","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.26000","title":"Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.17364","title":"A Polyak-Ruppert Central Limit Theorem for SA-Adam with Momentum and Non-Convergent Adaptive Preconditioning","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2607.05316","title":"How Much is Left? LLMs Linearly Encode Their Remaining Output Length","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2302.09727","title":"Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2310.19119","title":"Out-of-distribution Object Detection through Bayesian Uncertainty Estimation","created":"2023-10-29","cited_by_count":1,"area":null},{"id":"2311.14120","title":"Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2405.12553","title":"Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2405.18284","title":"Adaptive debiased SGD in high-dimensional GLMs with streaming data","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2410.17297","title":"Error estimates between SGD with momentum and underdamped Langevin diffusion","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2505.08125","title":"Sharp Gaussian approximations for Decentralized Federated Learning","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2510.19734","title":"Statistical Inference for Linear Functionals of Online Least-squares SGD when $t \\gtrsim d^{1+\\delta}$","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2604.07323","title":"Gaussian Approximation for Asynchronous Q-learning","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2606.01257","title":"Statistical Inference on Gradient Flows","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2310.11065","title":"Cheap Bootstrap for Fast Uncertainty Quantification of Stochastic Gradient Descent","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2312.09639","title":"Multiple Instance Learning for Uplift Modeling","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2403.11163","title":"A Selective Review on Statistical Methods for Massive Data Computation: Distributed Computing, Subsampling, and Minibatch Techniques","created":"2024-03-17","cited_by_count":0,"area":null},{"id":"2407.10955","title":"Enhancing Stochastic Optimization for Statistical Efficiency Using ROOT-SGD with Diminishing Stepsize","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2503.02178","title":"Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2505.18327","title":"Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2509.11039","title":"Convergence Rate in Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2603.20696","title":"High-dimensional online learning via asynchronous decomposition: Non-divergent results, dynamic regularization, and beyond","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2604.10814","title":"Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.21203","title":"Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.08864","title":"Higher-Order Equilibrium Tracking for EM-Compressible Online Estimation","created":"2026-05-09","cited_by_count":0,"area":null}],"next_cursor":null}