conftrace_

tail decay

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large deviations theory (1) beta mixing (1) orlicz space (1) dependent data (1) empirical risk minimizer (1) heavy-tailed noise (1) gradient clipping (1) square loss (1) non-convex optimization (1) stochastic gradient descent (1)

Papers

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization COLT 2026 Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss ICML 2024