Gaussian Limits for SGD Without Stationary Moments
stat.ML, cs.LG
Submitted: 2026-10-04
Updated: 2026-10-04
Sources
- Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains
- Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
- On the Rate of Gaussian Approximation for Linear Regression Problems
- Convergence and concentration properties of constant step-size SGD through Markov chains
- One-dimensional linear recursions with Markov-dependent coefficients
- SGD with Dependent Data: Optimal Estimation, Regret, and Inference
- Constant-Stepsize Stochastic Approximation: Finite-Time Convergence, Gaussian Approximation, and Tail Bounds
- Martingale approximations for sums of stationary processes
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