Towards optimisers that 'Keep Learning'

Emma Hart; Ian Miguel; Christopher Stone; Quentin Renau

doi:10.1145/3583133.3596344

Towards optimisers that 'Keep Learning'

Emma Hart, Ian Miguel, Christopher Stone, Quentin Renau

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and learning how to both predict and react to instance and/or domain drift.

Original language	English
Title of host publication	GECCO '23 companion
Subtitle of host publication	proceedings of the Companion Conference on Genetic and Evolutionary Computation
Editors	Sara Silva, Luís Paquete
Place of Publication	New York, NY
Publisher	ACM
Pages	1636-1638
Number of pages	3
ISBN (Electronic)	9798400701207
DOIs	https://doi.org/10.1145/3583133.3596344
Publication status	Published - 24 Jul 2023
Event	Genetic and Evolutionary Computation Conference 2023 (GECCO'23) - Lisbon, Portugal Duration: 15 Jul 2023 → 19 Jul 2023 https://gecco-2023.sigevo.org/HomePage

Conference

Conference	Genetic and Evolutionary Computation Conference 2023 (GECCO'23)
Country/Territory	Portugal
City	Lisbon
Period	15/07/23 → 19/07/23
Internet address	https://gecco-2023.sigevo.org/HomePage

Access to Document

10.1145/3583133.3596344

Cite this

@inproceedings{632785ed2d424e70894b76b11521006a,

title = "Towards optimisers that 'Keep Learning'",

abstract = "We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and learning how to both predict and react to instance and/or domain drift.",

author = "Emma Hart and Ian Miguel and Christopher Stone and Quentin Renau",

note = "Funding: The authors are funded by the EPSRC {\textquoteleft}Keep-Learning{\textquoteright} project: EP/V026534/1 and EP/V027182/1.; Genetic and Evolutionary Computation Conference 2023 (GECCO'23) ; Conference date: 15-07-2023 Through 19-07-2023",

year = "2023",

month = jul,

day = "24",

doi = "10.1145/3583133.3596344",

language = "English",

pages = "1636--1638",

editor = "Sara Silva and Lu{\'i}s Paquete",

booktitle = "GECCO '23 companion",

publisher = "ACM",

address = "United States",

url = "https://gecco-2023.sigevo.org/HomePage",

}

Hart, E, Miguel, I , Stone, C & Renau, Q 2023, Towards optimisers that 'Keep Learning'. in S Silva & L Paquete (eds), GECCO '23 companion: proceedings of the Companion Conference on Genetic and Evolutionary Computation. ACM, New York, NY, pp. 1636-1638, Genetic and Evolutionary Computation Conference 2023 (GECCO'23), Lisbon, Portugal, 15/07/23. https://doi.org/10.1145/3583133.3596344

TY - GEN

T1 - Towards optimisers that 'Keep Learning'

AU - Hart, Emma

AU - Miguel, Ian

AU - Stone, Christopher

AU - Renau, Quentin

N1 - Funding: The authors are funded by the EPSRC ‘Keep-Learning’ project: EP/V026534/1 and EP/V027182/1.

PY - 2023/7/24

Y1 - 2023/7/24

N2 - We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and learning how to both predict and react to instance and/or domain drift.

AB - We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and learning how to both predict and react to instance and/or domain drift.

UR - https://doi.org/10.1145/3583133

U2 - 10.1145/3583133.3596344

DO - 10.1145/3583133.3596344

M3 - Conference contribution

SP - 1636

EP - 1638

BT - GECCO '23 companion

A2 - Silva, Sara

A2 - Paquete, Luís

PB - ACM

CY - New York, NY

T2 - Genetic and Evolutionary Computation Conference 2023 (GECCO'23)

Y2 - 15 July 2023 through 19 July 2023

ER -

Towards optimisers that 'Keep Learning'

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Keep Learning: Keep Learning

Cite this

Towards optimisers that 'Keep Learning'

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

Keep Learning: Keep Learning

Cite this