Parallel Black-Box Complexity with Tail Bounds

01/31/2019
by   Per Kristian Lehre, et al.
6

We propose a new black-box complexity model for search algorithms evaluating λ search points in parallel. The parallel unary unbiased black-box complexity gives lower bounds on the number of function evaluations every parallel unary unbiased black-box algorithm needs to optimise a given problem. It captures the inertia caused by offspring populations in evolutionary algorithms and the total computational effort in parallel metaheuristics. We present complexity results for LeadingOnes and OneMax. Our main result is a general performance limit: we prove that on every function every λ-parallel unary unbiased algorithm needs at least Ω(λ n/λ + n n) evaluations to find any desired target set of up to exponential size, with an overwhelming probability. This yields lower bounds for the typical optimisation time on unimodal and multimodal problems, for the time to find any local optimum, and for the time to even get close to any optimum. The power and versatility of this approach is shown for a wide range of illustrative problems from combinatorial optimisation. Our performance limits can guide parameter choice and algorithm design; we demonstrate the latter by presenting an optimal λ-parallel algorithm for OneMax that uses parallelism most effectively.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/27/2015

Introducing Elitist Black-Box Models: When Does Elitist Selection Weaken the Performance of Evolutionary Algorithms?

Black-box complexity theory provides lower bounds for the runtime of bla...
research
08/10/2021

Asymptotic convergence rates for averaging strategies

Parallel black box optimization consists in estimating the optimum of a ...
research
03/06/2019

PBBFMM3D: a Parallel Black-Box Fast Multipole Method for Non-oscillatory Kernels

This paper presents PBBFMM3D: a parallel black-box fast multipole method...
research
04/15/2020

Automatic Generation of Algorithms for Black-Box Robust Optimisation Problems

We develop algorithms capable of tackling robust black-box optimisation ...
research
04/15/2018

Better Fixed-Arity Unbiased Black-Box Algorithms

In their GECCO'12 paper, Doerr and Doerr proved that the k-ary unbiased ...
research
05/25/2018

Parallel Architecture and Hyperparameter Search via Successive Halving and Classification

We present a simple and powerful algorithm for parallel black box optimi...
research
04/10/2015

OneMax in Black-Box Models with Several Restrictions

Black-box complexity studies lower bounds for the efficiency of general-...

Please sign up or login with your details

Forgot password? Click here to reset