Inexact Proximal Point Algorithms for Zeroth-Order Global Optimization

TL;DR

This paper develops inexact proximal point algorithms for zeroth-order global optimization of nonconvex functions, utilizing sampling and tensor train approximations to improve efficiency and provide convergence guarantees.

Contribution

It introduces a theoretical framework for inexact proximal point methods with convergence analysis, and proposes practical algorithms using sampling and tensor train techniques.

Findings

Convergence guarantees under mild assumptions.

Efficient low-rank tensor train approximation of functions.

Successful experiments on benchmark functions.

Abstract

This work concerns the zeroth-order global minimization of continuous nonconvex functions with a unique global minimizer and possibly multiple local minimizers. We formulate a theoretical framework for inexact proximal point (IPP) methods for global optimization, establishing convergence guarantees under mild assumptions when either deterministic or stochastic estimates of proximal operators are used. The quadratic regularization in the proximal operator and the scaling effect of a parameter $\delta>0$ create a concentrated landscape of an associated Gibbs measure that is practically effective for sampling. The convergence of the expectation under the Gibbs measure as $\delta\to 0^+$ is established, and the convergence rate of $\mathcal O(\delta)$ is derived under additional assumptions. These results provide a theoretical foundation for evaluating proximal operators inexactly using sampling-based methods such as Monte Carlo (MC) integration. In addition, we propose a new approach based on tensor train (TT) approximation. This approach employs a randomized TT cross algorithm to efficiently construct a low-rank TT approximation of a discretized function using a small number of function evaluations, and we provide an error analysis for the TT-based estimation. We then propose two practical IPP algorithms, TT-IPP and MC-IPP. The TT-IPP algorithm leverages TT estimates of the proximal operators, while the MC-IPP algorithm employs MC integration to estimate the proximal operators. Both algorithms are designed to adaptively balance efficiency and accuracy in inexact evaluations of proximal operators. The effectiveness of the two algorithms is demonstrated through experiments on diverse benchmark functions and various applications.