paper-with-me

홈 › Papers

Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms

2024-01-15 · Antoine Godichon-Baggioni, Wei Lu, Bruno Portier

This paper addresses second-order stochastic optimization for estimating the minimizer of a convex function written as an expectation. A direct recursive estimation technique for the inverse Hessian matrix using a Robbins-Monro procedure is introduced. This approach enables to drastically reduces computational complexity. Above all, it allows to develop universal stochastic Newton methods and investigate the asymptotic efficiency of the proposed approach. This work so expands the application scope of secondorder algorithms in stochastic optimization.

📄 PDF Abstract BibTeX arXiv:2401.10923

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods

2013-11-09 · Jascha Sohl-Dickstein, Ben Poole, Surya Ganguli

We present an algorithm for minimizing a sum of functions that combines the computational efficiency of stochastic gradient descent (SGD) with the second order curvature information leveraged by quasi-Newton methods. We …

Computational Efficiency

Stochastic Hessian Fittings with Lie Groups

2024-02-19 · Xi-Lin Li

This report investigates the fitting of Hessian or its inverse for stochastic optimizations using a Hessian fitting criterion derived from the preconditioned stochastic gradient descent (PSGD) method. This criterion is c…

Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation

2026-02-11 · Deyi Kong, Zaiwei Chen, Shuzhong Zhang, Shancong Mou arxiv

In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or a…

Bilevel Optimization

SPAN: A Stochastic Projected Approximate Newton Method

2020-02-10 · Xunpeng Huang, Xianfeng Liang, Zhengyang Liu, Yitan Li 외

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 approximat…

Quasi-Newton Steps for Efficient Online Exp-Concave Optimization

2022-11-02 · Zakaria Mhammedi, Khashayar Gatmiry

The aim of this paper is to design computationally-efficient and optimal algorithms for the online and stochastic exp-concave optimization settings. Typical algorithms for these settings, such as the Online Newton Step (…

Open-Ended Question Answering