Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pang, Yijiang, Yu, Shuyang, Hoang, Bao, Zhou, Jiayu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.04376
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913363775193088
author Pang, Yijiang
Yu, Shuyang
Hoang, Bao
Zhou, Jiayu
author_facet Pang, Yijiang
Yu, Shuyang
Hoang, Bao
Zhou, Jiayu
contents Hyperparameter tuning, particularly the selection of an appropriate learning rate in adaptive gradient training methods, remains a challenge. To tackle this challenge, in this paper, we propose a novel parameter-free optimizer, \textsc{AdamG} (Adam with the golden step size), designed to automatically adapt to diverse optimization problems without manual tuning. The core technique underlying \textsc{AdamG} is our golden step size derived for the AdaGrad-Norm algorithm, which is expected to help AdaGrad-Norm preserve the tuning-free convergence and approximate the optimal step size in expectation w.r.t. various optimization scenarios. To better evaluate tuning-free performance, we propose a novel evaluation criterion, \textit{reliability}, to comprehensively assess the efficacy of parameter-free optimizers in addition to classical performance criteria. Empirical results demonstrate that compared with other parameter-free baselines, \textsc{AdamG} achieves superior performance, which is consistently on par with Adam using a manually tuned learning rate across various optimization tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04376
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Stability of Parameter-free Optimization
Pang, Yijiang
Yu, Shuyang
Hoang, Bao
Zhou, Jiayu
Machine Learning
Hyperparameter tuning, particularly the selection of an appropriate learning rate in adaptive gradient training methods, remains a challenge. To tackle this challenge, in this paper, we propose a novel parameter-free optimizer, \textsc{AdamG} (Adam with the golden step size), designed to automatically adapt to diverse optimization problems without manual tuning. The core technique underlying \textsc{AdamG} is our golden step size derived for the AdaGrad-Norm algorithm, which is expected to help AdaGrad-Norm preserve the tuning-free convergence and approximate the optimal step size in expectation w.r.t. various optimization scenarios. To better evaluate tuning-free performance, we propose a novel evaluation criterion, \textit{reliability}, to comprehensively assess the efficacy of parameter-free optimizers in addition to classical performance criteria. Empirical results demonstrate that compared with other parameter-free baselines, \textsc{AdamG} achieves superior performance, which is consistently on par with Adam using a manually tuned learning rate across various optimization tasks.
title Towards Stability of Parameter-free Optimization
topic Machine Learning
url https://arxiv.org/abs/2405.04376