OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Yuan, Ganzhao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913037897695232
author Yuan, Ganzhao
author_facet Yuan, Ganzhao
contents The Exponential Moving Average (EMA) is a cornerstone of widely used optimizers such as Adam. However, existing theoretical analyses of Adam-style methods have notable limitations: their guarantees can remain suboptimal in the zero-noise regime, rely on restrictive boundedness conditions (e.g., bounded gradients or objective gaps), use constant or open-loop stepsizes, or require prior knowledge of Lipschitz constants. To overcome these bottlenecks, we introduce OptEMA and analyze two novel variants: OptEMA-M, which applies an adaptive, decreasing EMA coefficient to the first-order moment with a fixed second-order decay, and OptEMA-V, which swaps these roles. At the heart of these variants is a novel Corrected AdaGrad-Norm stepsize. This formulation renders OptEMA closed-loop and Lipschitz-free, meaning its effective stepsizes are strictly trajectory-dependent and require no parameterization via the Lipschitz constant. Under standard stochastic gradient descent (SGD) assumptions, namely smoothness, a lower-bounded objective, and unbiased gradients with bounded variance, we establish rigorous convergence guarantees. Both variants achieve a noise-adaptive convergence rate of $\widetilde{\mathcal{O}}(T^{-1/2}+σ^{1/2} T^{-1/4})$ for the average gradient norm, where $σ$ is the noise level. Crucially, the Corrected AdaGrad-Norm stepsize plays a central role in enabling the noise-adaptive guarantees: in the zero-noise regime ($σ=0$), our bounds automatically reduce to the nearly optimal deterministic rate $\widetilde{\mathcal{O}}(T^{-1/2})$ without any manual hyperparameter retuning.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09923
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
Yuan, Ganzhao
Machine Learning
Numerical Analysis
Optimization and Control
The Exponential Moving Average (EMA) is a cornerstone of widely used optimizers such as Adam. However, existing theoretical analyses of Adam-style methods have notable limitations: their guarantees can remain suboptimal in the zero-noise regime, rely on restrictive boundedness conditions (e.g., bounded gradients or objective gaps), use constant or open-loop stepsizes, or require prior knowledge of Lipschitz constants. To overcome these bottlenecks, we introduce OptEMA and analyze two novel variants: OptEMA-M, which applies an adaptive, decreasing EMA coefficient to the first-order moment with a fixed second-order decay, and OptEMA-V, which swaps these roles. At the heart of these variants is a novel Corrected AdaGrad-Norm stepsize. This formulation renders OptEMA closed-loop and Lipschitz-free, meaning its effective stepsizes are strictly trajectory-dependent and require no parameterization via the Lipschitz constant. Under standard stochastic gradient descent (SGD) assumptions, namely smoothness, a lower-bounded objective, and unbiased gradients with bounded variance, we establish rigorous convergence guarantees. Both variants achieve a noise-adaptive convergence rate of $\widetilde{\mathcal{O}}(T^{-1/2}+σ^{1/2} T^{-1/4})$ for the average gradient norm, where $σ$ is the noise level. Crucially, the Corrected AdaGrad-Norm stepsize plays a central role in enabling the noise-adaptive guarantees: in the zero-noise regime ($σ=0$), our bounds automatically reduce to the nearly optimal deterministic rate $\widetilde{\mathcal{O}}(T^{-1/2})$ without any manual hyperparameter retuning.
title OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
topic Machine Learning
Numerical Analysis
Optimization and Control
url https://arxiv.org/abs/2603.09923