paper-with-me

홈 › Papers

Gradient Methods with Online Scaling Part I. Theoretical Foundations

2025-05-29 · Wenzhi Gao, Ya-Chi Chu, Yinyu Ye, Madeleine Udell

This paper establishes the theoretical foundations of the online scaled gradient methods (OSGM), a framework that utilizes online learning to adapt stepsizes and provably accelerate first-order methods. OSGM quantifies the effectiveness of a stepsize by a feedback function motivated from a convergence measure and uses the feedback to adjust the stepsize through an online learning algorithm. Consequently, instantiations of OSGM achieve convergence rates that are asymptotically no worse than the optimal stepsize. OSGM yields desirable convergence guarantees on smooth convex problems, including 1) trajectory-dependent global convergence on smooth convex objectives; 2) an improved complexity result on smooth strongly convex problems, and 3) local superlinear convergence. Notably, OSGM constitutes a new family of first-order methods with non-asymptotic superlinear convergence, joining the celebrated quasi-Newton methods. Finally, OSGM explains the empirical success of the popular hypergradient-descent heuristic in optimization for machine learning.

📄 PDF Abstract BibTeX arXiv:2505.23081

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Gradient Methods with Online Scaling

2024-11-04 · Wenzhi Gao, Ya-Chi Chu, Yinyu Ye, Madeleine Udell

We introduce a framework to accelerate the convergence of gradient-based methods with online learning. The framework learns to scale the gradient at each iteration through an online learning algorithm and provably accele…

Gradient Methods with Online Scaling Part II. Practical Aspects

2025-09-13 · Ya-Chi Chu, Wenzhi Gao, Yinyu Ye, Madeleine Udell arxiv

Part I of this work [Gao25] establishes online scaled gradient methods (OSGM), a framework that utilizes online convex optimization to adapt stepsizes in gradient methods. This paper focuses on the practical aspects of O…

Gradient-based Hyperparameter Optimization Over Long Horizons

2020-07-15 · NeurIPS 2021 12 · Paul Micaelli, Amos Storkey

Gradient-based hyperparameter optimization has earned a widespread popularity in the context of few-shot meta-learning, but remains broadly impractical for tasks with long horizons (many gradient steps), due to memory sc…

Hyperparameter OptimizationMeta-Learning

Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight

2024-11-05 · Tao Huang, Qingyu Huang, Xin Shi, Jiayang Meng 외

In the domain of deep learning, the challenge of protecting sensitive data while maintaining model utility is significant. Traditional Differential Privacy (DP) techniques such as Differentially Private Stochastic Gradie…

A Graph Autoencoder Approach to Causal Structure Learning

2019-11-18 · Ignavier Ng, Shengyu Zhu, Zhitang Chen, Zhuangyan Fang

Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new appro…