paper-with-me

홈 › Papers

Quasi-Quadratic Gradient: A New Direction for Accelerating the BFGS Method in Quasi-Newton Optimization

2026-04-27 · John Chiang arxiv

In this paper, we introduce the Quasi-Quadratic Gradient (QQG), a novel search direction designed to accelerate the BFGS method within the quasi-Newton framework. By defining the QQG as the product of the inverse Hessian approximation and the current gradient, we explicitly leverage local second-order curvature to rectify the search path. Theoretical analysis and empirical results demonstrate that our approach significantly outperforms vanilla BFGS in convergence speed while maintaining computational efficiency.

📄 PDF Abstract BibTeX arXiv:2604.23922

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

A Progressive Batching L-BFGS Method for Machine Learning

2018-02-15 · ICML 2018 7 · Raghu Bollapragada, Dheevatsa Mudigere, Jorge Nocedal, Hao-Jun Michael Shi 외

The standard L-BFGS method relies on gradient approximations that are not dominated by noise, so that search directions are descent directions, the line search is reliable, and quasi-Newton updating yields useful quadrat…

BIG-bench Machine Learning

Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence

2021-12-01 · NeurIPS 2021 12 · Dachao Lin, Haishan Ye, Zhihua Zhang

In this paper, we follow Rodomanov and Nesterov’s work to study quasi-Newton methods. We focus on the common SR1 and BFGS quasi-Newton methods to establish better explicit (local) superlinear convergence rates. First, ba…

Quasi-Newton Optimization Methods For Deep Learning Applications

2019-09-04 · Jacob Rafati, Roummel F. Marcia

Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and de…

Deep LearningDeep Reinforcement Learningimage-classificationImage Classification+4

mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization

2023-07-25 · Yue Niu, Zalan Fabian, Sunwoo Lee, Mahdi Soltanolkotabi 외

Quasi-Newton methods still face significant challenges in training large-scale neural networks due to additional compute costs in the Hessian related computations and instability issues in stochastic training. A well-kno…

Stochastic Optimization

Practical Quasi-Newton Methods for Training Deep Neural Networks

2020-06-16 · NeurIPS 2020 12 · Donald Goldfarb, Yi Ren, Achraf Bahamou

We consider the development of practical stochastic quasi-Newton, and in particular Kronecker-factored block-diagonal BFGS and L-BFGS methods, for training deep neural networks (DNNs). In DNN training, the number of vari…