Lower Bounds on Inference Complexity for Polyak-Ruppert Averaged Stochastic Gradient Descent
stat.ML, cs.LG, math.OC, math.ST, stat.TH
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation
- Berry--Esseen bounds for stochastic approximation with Markovian noise
- Gaussian Limits for SGD Without Stationary Moments
- Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression
- Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD
- Constant-Stepsize Stochastic Approximation: Finite-Time Convergence, Gaussian Approximation, and Tail Bounds
- High Confidence Level Inference is Almost Free using Parallel Stochastic Optimization
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference