conftrace_

averaged stochastic gradient descent

2 papers

Explore in graph

Also known as

ASGD

Co-occurring keywords · papers mentioning both

nagaev bound (1) sub-gaussian noise (1) concentration analysis (1) heavy-tailed noise (1) minimax optimal rate (1) relu network (1) error bound (1) concentration bound (1) gradient descent optimization (1) reproducing kernel hilbert space (1)

Papers

Beyond Sub-Gaussian Noises: Sharp Concentration Analysis for Stochastic Gradient Descent JMLR 2022 Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime ICLR 2021