Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach

TL;DR

This paper introduces an adaptive sample size approach that leverages the local superlinear convergence of quasi-Newton methods to efficiently solve large-scale empirical risk minimization problems throughout the entire learning process.

Contribution

It proposes a novel adaptive sample size scheme that exploits quasi-Newton methods' superlinear convergence globally, improving efficiency in large-scale ERM problems.

Findings

Superlinear convergence achieved after at most three iterations per subproblem.

Method outperforms traditional approaches in computational efficiency.

Numerical experiments confirm theoretical convergence and advantages.

Abstract

In this paper, we study the application of quasi-Newton methods for solving empirical risk minimization (ERM) problems defined over a large dataset. Traditional deterministic and stochastic quasi-Newton methods can be executed to solve such problems; however, it is known that their global convergence rate may not be better than first-order methods, and their local superlinear convergence only appears towards the end of the learning process. In this paper, we use an adaptive sample size scheme that exploits the superlinear convergence of quasi-Newton methods globally and throughout the entire learning process. The main idea of the proposed adaptive sample size algorithms is to start with a small subset of data points and solve their corresponding ERM problem within its statistical accuracy, and then enlarge the sample size geometrically and use the optimal solution of the problem corresponding to the smaller set as an initial point for solving the subsequent ERM problem with more samples. We show that if the initial sample size is sufficiently large and we use quasi-Newton methods to solve each subproblem, the subproblems can be solved superlinearly fast (after at most three iterations), as we guarantee that the iterates always stay within a neighborhood that quasi-Newton methods converge superlinearly. Numerical experiments on various datasets confirm our theoretical results and demonstrate the computational advantages of our method.