Salvato in:
Dettagli Bibliografici
Autori principali: Yao, Zhipeng, Yu, Rui, Chang, Guisong, Li, Ying, Zhang, Yu, Li, Dazhou
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.06120
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908870171951104
author Yao, Zhipeng
Yu, Rui
Chang, Guisong
Li, Ying
Zhang, Yu
Li, Dazhou
author_facet Yao, Zhipeng
Yu, Rui
Chang, Guisong
Li, Ying
Zhang, Yu
Li, Dazhou
contents Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fixed momentum coefficients inherently distort the balance between bias and variance, leading to skewed or suboptimal parameter updates. To address this, we propose SGDF (SGD with Filter), an optimizer inspired by the principles of Optimal Linear Filtering. SGDF computes an online, time-varying gain to dynamically refine gradient estimation by minimizing the mean-squared error, thereby achieving an optimal trade-off between noise suppression and signal preservation. Furthermore, our approach could extend to other optimizers, showcasing its broad applicability to optimization frameworks. Extensive experiments across diverse architectures and benchmarks demonstrate SGDF surpasses conventional momentum methods and achieves performance on par with or surpassing state-of-the-art optimizers.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06120
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dynamic Momentum Recalibration in Online Gradient Learning
Yao, Zhipeng
Yu, Rui
Chang, Guisong
Li, Ying
Zhang, Yu
Li, Dazhou
Machine Learning
Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fixed momentum coefficients inherently distort the balance between bias and variance, leading to skewed or suboptimal parameter updates. To address this, we propose SGDF (SGD with Filter), an optimizer inspired by the principles of Optimal Linear Filtering. SGDF computes an online, time-varying gain to dynamically refine gradient estimation by minimizing the mean-squared error, thereby achieving an optimal trade-off between noise suppression and signal preservation. Furthermore, our approach could extend to other optimizers, showcasing its broad applicability to optimization frameworks. Extensive experiments across diverse architectures and benchmarks demonstrate SGDF surpasses conventional momentum methods and achieves performance on par with or surpassing state-of-the-art optimizers.
title Dynamic Momentum Recalibration in Online Gradient Learning
topic Machine Learning
url https://arxiv.org/abs/2603.06120