Paper
Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients
A theoretical paper that studies the tail behavior of nonlinear stochastic gradient descent under infinite-variance gradients and establishes exact first-order tail probability laws for the last iterate.
Timeline (last 90 days)
Oct 19
The paper 'Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients' establishes exact first-order tail probabilities for the last iterate of nonlinear, constant-step-size SGD.
Unverified50%