Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Gaussian Limits for SGD Without Stationary Moments
Xiaoli Li, Wei Biao Wu
Temporal dependence can separate the Gaussian approximation of stochastic gradient descent from its stationary moments. For unmodified least-squares SGD, we construct a design with…
stat.ML2026
Moment-Accurate Gaussian Mixtures for Constant-Step Stochastic Approximation
Xiaoli Li, Wei Biao Wu
Local Gaussian models of constant-step learning predict output variability and expected losses, but weak convergence alone does not justify these moment predictions. We establish m…