paper-with-me

홈 › Papers

Robust empirical risk minimization via Newton's method

2023-01-30 · Eirini Ioannou, Muni Sreenivas Pydi, Po-Ling Loh

A new variant of Newton's method for empirical risk minimization is studied, where at each iteration of the optimization algorithm, the gradient and Hessian of the objective function are replaced by robust estimators taken from existing literature on robust mean estimation for multivariate data. After proving a general theorem about the convergence of successive iterates to a small ball around the population-level minimizer, consequences of the theory in generalized linear models are studied when data are generated from Huber's epsilon-contamination model and/or heavytailed distributions. An algorithm for obtaining robust Newton directions based on the conjugate gradient method is also proposed, which may be more appropriate for high-dimensional settings, and conjectures about the convergence of the resulting algorithm are offered. Compared to robust gradient descent, the proposed algorithm enjoys the faster rates of convergence for successive iterates often achieved by second-order algorithms for convex problems, i.e., quadratic convergence in a neighborhood of the optimum, with a stepsize that may be chosen adaptively via backtracking linesearch.

📄 PDF Abstract BibTeX arXiv:2301.13192

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy

2016-05-24 · NeurIPS 2016 12 · Aryan Mokhtari, Alejandro Ribeiro

We consider empirical risk minimization for large-scale datasets. We introduce Ada Newton as an adaptive algorithm that uses Newton's method with adaptive sample sizes. The main idea of Ada Newton is to increase the size…

Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches

2022-06-06 · Michał Dereziński

Stochastic variance reduction has proven effective at accelerating first-order algorithms for solving convex finite-sum optimization tasks such as empirical risk minimization. Incorporating second-order information has p…

Second-order methods

Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method

2017-05-22 · Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro

We consider large scale empirical risk minimization (ERM) problems, where both the problem dimension and variable size is large. In these cases, most second order methods are infeasible due to the high cost in both compu…

Second-order methods

GIANT: Globally Improved Approximate Newton Method for Distributed Optimization

2017-09-11 · NeurIPS 2018 12 · Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney

For distributed computing environment, we consider the empirical risk minimization problem and propose a distributed and communication-efficient Newton-type optimization method. At every iteration, each worker locally fi…

Distributed ComputingDistributed Optimization

RFN: A Random-Feature Based Newton Method for Empirical Risk Minimization in Reproducing Kernel Hilbert Spaces

2020-02-12 · Ting-Jui Chang, Shahin Shahrampour

In supervised learning using kernel methods, we often encounter a large-scale finite-sum minimization over a reproducing kernel Hilbert space (RKHS). Large-scale finite-sum problems can be solved using efficient variants…