2023
DOI: 10.48550/arxiv.2301.12457
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

EvoX: A Distributed GPU-accelerated Library towards Scalable Evolutionary Computation

Abstract: During the past decades, evolutionary computation (EC) has demonstrated promising potential in solving various complex optimization problems of relatively small scales. Nowadays, however, ongoing developments in modern science and engineering are bringing increasingly grave challenges to the conventional EC paradigm in terms of scalability. As problem scales increase, on the one hand, the encoding spaces (i.e., dimensions of the decision vectors) are intrinsically larger; on the other hand, EC algorithms often… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 40 publications
0
1
0
Order By: Relevance
“…It facilitates researchers to design multi-objective EAs to deal with various types of multiobjective optimization problems. EvoX [29] is a distributed GPU-accelerated library that helps researchers design parallel EAs to accelerate the solving of complex optimization problems and training for reinforcement learning. However, different from the traditional single-task EC field, solving MTO problems with MTEAs requires simultaneous evolution of multiple optimization tasks with inter-task solution space mapping and knowledge transfer.…”
Section: Introductionmentioning
confidence: 99%
“…It facilitates researchers to design multi-objective EAs to deal with various types of multiobjective optimization problems. EvoX [29] is a distributed GPU-accelerated library that helps researchers design parallel EAs to accelerate the solving of complex optimization problems and training for reinforcement learning. However, different from the traditional single-task EC field, solving MTO problems with MTEAs requires simultaneous evolution of multiple optimization tasks with inter-task solution space mapping and knowledge transfer.…”
Section: Introductionmentioning
confidence: 99%