Unverified50% confidenceFactExact time
The paper proves that the SGD iterates converge to a stable OU process at the central fluctuation scale and uses this limit to characterize the tail probabilities.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 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.72% similarUnverifiedThe paper proves that the classical Local Extra SGD algorithm, through more refined analysis, can achieve tighter convergence guarantees than previously known for general smooth and monotone variational inequalities.72% similarUnverifiedWhen ε ≈ 1, the gradient second-moment term in the denominator is diluted, adaptive scaling has almost no effect, and the optimizer behaves close to pure SGD.72% similarUnverifiedStochastic gradient descent (SGD) is a cornerstone of machine learning optimization, and rigorous analysis of its convergence rate usually relies on cumbersome probabilistic derivations such as martingale theory or concentration inequalities.71% similarUnverifiedClassical stochastic approximation theory relies on the Robbins-Monro conditions to guarantee convergence, but SGDM with a constant step size does not satisfy these conditions, and the parameters keep fluctuating around a steady state rather than converging to a point.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064977API
curl https://kongchang.com/api/v1/knowledge/claims/1064977MCP
get_claim(id=1064977)