On the Non-convergence of Differential Evolution: Some generalized adversarial conditions and a remedy

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F19%3A10244225" target="_blank" >RIV/61989100:27240/19:10244225 - isvavai.cz</a>

Výsledek na webu

<a href="https://dl.acm.org/doi/abs/10.1145/3319619.3322007?casa_token=54gaX4AOl_cAAAAA:L5VQpAW1yDg6uk6VtGSWi8aVsThk_3gkmlMGbbNLt6dPdMsbSpAYguM6XfqE1H1YaddDhaAYA8B1cA" target="_blank" >https://dl.acm.org/doi/abs/10.1145/3319619.3322007?casa_token=54gaX4AOl_cAAAAA:L5VQpAW1yDg6uk6VtGSWi8aVsThk_3gkmlMGbbNLt6dPdMsbSpAYguM6XfqE1H1YaddDhaAYA8B1cA</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3319619.3322007" target="_blank" >10.1145/3319619.3322007</a>

Jazyk výsledku

angličtina

Název v původním jazyce

On the Non-convergence of Differential Evolution: Some generalized adversarial conditions and a remedy

Popis výsledku v původním jazyce

In this paper, we analyze the convergence behavior of Differential Evolution (DE) and theoretically prove that under certain adversarial conditions, the generic DE algorithm may not at all converge to the global optimum even on apparently simpler fitness landscapes. We characterize these function classes and initialization conditions theoretically and provide mathematical supports to the non-convergence behavior of DE. To overcome these adversarial conditions, we propose a slightly modified variant of DE called Differential Evolution with Noisy Mutation (DENM), which incorporates a noise term in the mutation step. We analytically show that DENM can converge to the global optima within a finite budget of function evaluations. (C) 2019 Association for Computing Machinery. ACM ISBN 978-1-4503-6748-6/19/07...$15.00...$15.00

Název v anglickém jazyce

On the Non-convergence of Differential Evolution: Some generalized adversarial conditions and a remedy

Popis výsledku anglicky

In this paper, we analyze the convergence behavior of Differential Evolution (DE) and theoretically prove that under certain adversarial conditions, the generic DE algorithm may not at all converge to the global optimum even on apparently simpler fitness landscapes. We characterize these function classes and initialization conditions theoretically and provide mathematical supports to the non-convergence behavior of DE. To overcome these adversarial conditions, we propose a slightly modified variant of DE called Differential Evolution with Noisy Mutation (DENM), which incorporates a noise term in the mutation step. We analytically show that DENM can converge to the global optima within a finite budget of function evaluations. (C) 2019 Association for Computing Machinery. ACM ISBN 978-1-4503-6748-6/19/07...$15.00...$15.00

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

ISBN

978-1-4503-6748-6

ISSN

—

e-ISSN

—

Počet stran výsledku

2

Strana od-do

265-266

Název nakladatele

Association for Computing Machinery

Místo vydání

New York

Místo konání akce

Praha

Datum konání akce

13. 7. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—