Preprint
Oct 2026
Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients
This work describes its accuracy through exact first-order tail probabilities for the last iterate of nonlinear, constant-stepsize SGD, and proves its relative accuracy at shrinking tolerances above the central scale, with state-dependent noise and a growing observation horizon.
Xiao-Lin Li, Qi Lei, Zi-Yang Wei et al.
· 0 citations