Proving μ>1

04/24/2020
by   Laurent Meunier, et al.
0

Choosing the right selection rate is a long standing issue in evolutionary computation. In the continuous unconstrained case, we prove mathematically that μ=1 leads to a sub-optimal simple regret in the case of the sphere function. We provide a theoretically-based selection rate μ/λ that leads to better convergence rates. With our choice of selection rate, we get a provable regret of order O(λ^-1) which has to be compared with O(λ^-2/d) in the case where μ=1. We complete our study with experiments to confirm our theoretical claims.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2020

Tight last-iterate convergence rates for no-regret learning in multi-player games

We study the question of obtaining last-iterate convergence rates for no...
research
05/17/2018

Faster Rates for Convex-Concave Games

We consider the use of no-regret algorithms to compute equilibria for pa...
research
07/22/2019

Convergence Rates of Posterior Distributions in Markov Decision Process

In this paper, we show the convergence rates of posterior distributions ...
research
10/09/2019

Robust Monopoly Regulation

We study the regulation of a monopolistic firm using a robust-design app...
research
06/19/2019

XNAS: Neural Architecture Search with Expert Advice

This paper introduces a novel optimization method for differential neura...
research
11/08/2022

Stability estimates for the expected utility in Bayesian optimal experimental design

We study stability properties of the expected utility function in Bayesi...
research
02/28/2018

RRR: Rank-Regret Representative

We propose the rank-regret representative as a way of choosing a small s...

Please sign up or login with your details

Forgot password? Click here to reset