paper-with-me

Papers

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 OSGM. We leverage the OSGM framework to design new adaptive first-order methods and provide insights into their empirical behavior. The resulting method, OSGM-Best, matches the performance of quasi-Newton variants while requiring less memory and cheaper iterations. We also extend OSGM to nonconvex optimization and outline directions that connect OSGM to existing branches of optimization theory and practice.

📄 PDF Abstract BibTeX arXiv:2509.11007

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…

A Truly Sparse and General Implementation of Gradient-Based Synaptic Plasticity

2025-01-20 · Jamie Lohoff, Anil Kaya, Florian Assmuth, Emre Neftci

Online synaptic plasticity rules derived from gradient descent achieve high accuracy on a wide range of practical tasks. However, their software implementation often requires tediously hand-derived gradients or using gra…

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

Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA

2017-12-08 · Chuang Wang, Jonathan Mattingly, Yue M. Lu

We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regressi…

The Scaling Limit of High-Dimensional Online Independent Component Analysis

2017-10-15 · NeurIPS 2017 12 · Chuang Wang, Yue M. Lu

We analyze the dynamics of an online algorithm for independent component analysis in the high-dimensional scaling limit. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-var…

Vocal Bursts Intensity Prediction