DeepAI AI Chat
Log In Sign Up

Convergence rate of the (1+1)-evolution strategy on locally strongly convex functions with lipschitz continuous gradient and their monotonic transformations

09/26/2022
by   Daiki Morinaga, et al.
0

Evolution strategy (ES) is one of promising classes of algorithms for black-box continuous optimization. Despite its broad successes in applications, theoretical analysis on the speed of its convergence is limited on convex quadratic functions and their monotonic transformation. In this study, an upper bound and a lower bound of the rate of linear convergence of the (1+1)-ES on locally L-strongly convex functions with U-Lipschitz continuous gradient are derived as exp(-Ω_d→∞(L/d· U)) and exp(-1/d), respectively. Notably, any prior knowledge on the mathematical properties of the objective function such as Lipschitz constant is not given to the algorithm, whereas the existing analyses of derivative-free optimization algorithms require them.

READ FULL TEXT
09/18/2020

Global Linear Convergence of Evolution Strategies on More Than Smooth Strongly Convex Functions

Evolution strategies (ESs) are zero-order stochastic black-box optimizat...
01/13/2018

An Explicit Convergence Rate for Nesterov's Method from SDP

The framework of Integral Quadratic Constraints (IQC) introduced by Less...
04/06/2022

Black-Box Min–Max Continuous Optimization Using CMA-ES with Worst-case Ranking Approximation

In this study, we investigate the problem of min-max continuous optimiza...
04/17/2022

A Modified Nonlinear Conjugate Gradient Algorithm for Functions with Non-Lipschitz Gradient

In this paper, we propose a modified nonlinear conjugate gradient (NCG) ...
07/17/2016

Global Continuous Optimization with Error Bound and Fast Convergence

This paper considers global optimization with a black-box unknown object...
05/23/2023

Revisiting Subgradient Method: Complexity and Convergence Beyond Lipschitz Continuity

The subgradient method is one of the most fundamental algorithmic scheme...
06/17/2019

On linear convergence of two decentralized algorithms

Decentralized algorithms solve multi-agent problems over a connected net...