Strong Gaussian Approximation of Constant Learning Rate SGD: Bias and Trajectory Inference
stat.ML, cs.LG
Submitted: 2026-10-10
Updated: 2026-10-14
Sources
- Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains
- Functional Central Limit Theorem for Stochastic Gradient Descent
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
- Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD
- Online Covariance Matrix Estimation in Stochastic Gradient Descent
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier