Answers are grounded in this paper and cite their sources.
Stochastic gradient descent with momentum is a popular variant of stochastic gradient descent, which has recently been reported to have a close relationship with the underdamped Langevin diffusion. In this paper, we establish time-uniform error bounds between them in the 1-Wasserstein and total variation distances. Leveraging Malliavin analysis and the exponential ergodicity of the underdamped Langevin diffusion, we characterize the long-time behavior of this algorithm, even for nonconvex objective functions.
No takes yet. Share an insight, caveat, or question.
Guillin et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: