A Rate Transfer Method: Convergence Rates in Stochastic Gradient Descent via Stochastic Calculus
Neil Walton
Oct 2026
Artificial Intelligence
Machine Learning
Data Science
Abstract
We develop a rate-transfer method that converts finite-time Lyapunov estimates for an associated stochastic differential equation (SDE) into finite-time convergence bounds for stochastic gradient algorithms. Under generic moment and smoothness conditions, the convergence analysis of the stochastic gradient method reduces to a calculus argument verifying a Lyapunov generator inequality for the SDE. The method recovers established rates for classical stochastic gradient methods and provides a way to establish convergence rates for new optimization algorithms through calculus arguments applied to their associated SDEs.
![Director of Machine Learning Insights [Part 4]](/uploads/articles/4d4046d553c83e57a3aa9af0665a2d2d482ad7c9.png)