paper-with-me

홈 › Papers

SPAN: A Stochastic Projected Approximate Newton Method

2020-02-10 · Xunpeng Huang, Xianfeng Liang, Zhengyang Liu, Yitan Li, Linyun Yu, Yue Yu, Lei LI

Second-order optimization methods have desirable convergence properties. However, the exact Newton method requires expensive computation for the Hessian and its inverse. In this paper, we propose SPAN, a novel approximate and fast Newton method. SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products. Our experiments on multiple benchmark datasets demonstrate that SPAN outperforms existing first-order and second-order optimization methods in terms of the convergence wall-clock time. Furthermore, we provide a theoretical analysis of the per-iteration complexity, the approximation error, and the convergence rate. Both the theoretical analysis and experimental results show that our proposed method achieves a better trade-off between the convergence rate and the per-iteration efficiency.

📄 PDF Abstract BibTeX arXiv:2002.03687

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stochastic model-based minimization of weakly convex functions

2018-03-17 · Damek Davis, Dmitriy Drusvyatskiy

We consider a family of algorithms that successively sample and minimize simple stochastic models of the objective function. We show that under reasonable conditions on approximation quality and regularity of the models,…

model

Nys-Newton: Nyström-Approximated Curvature for Stochastic Optimization

2021-10-16 · Dinesh Singh, Hardik Tankaria, Makoto Yamada

Second-order optimization methods are among the most widely used optimization approaches for convex optimization problems, and have recently been used to optimize non-convex optimization problems such as deep learning mo…

Stochastic Optimization

A Variance Reduced Stochastic Newton Method

2015-03-28 · Aurelien Lucchi, Brian McWilliams, Thomas Hofmann

Quasi-Newton methods are widely used in practise for convex loss minimization problems. These methods exhibit good empirical performance on a wide variety of tasks and enjoy super-linear convergence to the optimal soluti…

Nesterov's Acceleration For Approximate Newton

2017-10-17 · Haishan Ye, Zhihua Zhang

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform po…

Second-order methods

Accelerating Dynamical System Simulations with Contracting and Physics-Projected Neural-Newton Solvers

2021-06-04 · Samuel Chevalier, Jochen Stiasny, Spyros Chatzivasileiadis

Recent advances in deep learning have allowed neural networks (NNs) to successfully replace traditional numerical solvers in many applications, thus enabling impressive computing gains. One such application is time domai…