META-SMGO-Δ: Similarity as a Prior in Black-Box Optimization

Riccardo Busetto; Valentina Breschi; Simone Formentin

doi:10.1109/CDC49753.2023.10383592

META-SMGO-Δ: Similarity as a Prior in Black-Box Optimization

Riccardo Busetto
, Valentina Breschi
, Simone Formentin

Control Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

32 Downloads (Pure)

Abstract

When solving global optimization problems in practice, one often ends up repeatedly solving problems that are similar to each others. By introducing a rigorous definition of similarity to exploit priors obtained from past experience to efficiently solve new (similar) problems, in this work we incorporate the META-learning rationale into SMGO -Δ, a global optimization approach recently proposed in the literature. Through a benchmark numerical example we show the practical benefits of our META -extension of the baseline algorithm, while providing theoretical bounds on its performance.

Original language	English
Title of host publication	2023 62nd IEEE Conference on Decision and Control, CDC 2023
Publisher	Institute of Electrical and Electronics Engineers
Pages	1294-1299
Number of pages	6
ISBN (Electronic)	979-8-3503-0124-3
DOIs	https://doi.org/10.1109/CDC49753.2023.10383592
Publication status	Published - 19 Jan 2024
Event	62nd IEEE Conference on Decision and Control, CDC 2023 - Singapore, Singapore Duration: 13 Dec 2023 → 15 Dec 2023 Conference number: 62

Conference

Conference	62nd IEEE Conference on Decision and Control, CDC 2023
Abbreviated title	CDC 2023
Country/Territory	Singapore
City	Singapore
Period	13/12/23 → 15/12/23

Access to Document

10.1109/CDC49753.2023.10383592

pdfFinal published version, 708 KBLicence: TAVERNE

Cite this

@inproceedings{3d7c49884de44d4d93b554e7a7f083be,

title = "META-SMGO-Δ: Similarity as a Prior in Black-Box Optimization",

abstract = "When solving global optimization problems in practice, one often ends up repeatedly solving problems that are similar to each others. By introducing a rigorous definition of similarity to exploit priors obtained from past experience to efficiently solve new (similar) problems, in this work we incorporate the META-learning rationale into SMGO -Δ, a global optimization approach recently proposed in the literature. Through a benchmark numerical example we show the practical benefits of our META -extension of the baseline algorithm, while providing theoretical bounds on its performance.",

author = "Riccardo Busetto and Valentina Breschi and Simone Formentin",

year = "2024",

month = jan,

day = "19",

doi = "10.1109/CDC49753.2023.10383592",

language = "English",

pages = "1294--1299",

booktitle = "2023 62nd IEEE Conference on Decision and Control, CDC 2023",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "62nd IEEE Conference on Decision and Control, CDC 2023, CDC 2023 ; Conference date: 13-12-2023 Through 15-12-2023",

}

Busetto, R, Breschi, V & Formentin, S 2024, META-SMGO-Δ: Similarity as a Prior in Black-Box Optimization. in 2023 62nd IEEE Conference on Decision and Control, CDC 2023., 10383592, Institute of Electrical and Electronics Engineers, pp. 1294-1299, 62nd IEEE Conference on Decision and Control, CDC 2023, Singapore, Singapore, 13/12/23. https://doi.org/10.1109/CDC49753.2023.10383592

META-SMGO-Δ: Similarity as a Prior in Black-Box Optimization. / Busetto, Riccardo; Breschi, Valentina; Formentin, Simone.
2023 62nd IEEE Conference on Decision and Control, CDC 2023. Institute of Electrical and Electronics Engineers, 2024. p. 1294-1299 10383592.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - META-SMGO-Δ

T2 - 62nd IEEE Conference on Decision and Control, CDC 2023

AU - Busetto, Riccardo

AU - Breschi, Valentina

AU - Formentin, Simone

N1 - Conference code: 62

PY - 2024/1/19

Y1 - 2024/1/19

N2 - When solving global optimization problems in practice, one often ends up repeatedly solving problems that are similar to each others. By introducing a rigorous definition of similarity to exploit priors obtained from past experience to efficiently solve new (similar) problems, in this work we incorporate the META-learning rationale into SMGO -Δ, a global optimization approach recently proposed in the literature. Through a benchmark numerical example we show the practical benefits of our META -extension of the baseline algorithm, while providing theoretical bounds on its performance.

AB - When solving global optimization problems in practice, one often ends up repeatedly solving problems that are similar to each others. By introducing a rigorous definition of similarity to exploit priors obtained from past experience to efficiently solve new (similar) problems, in this work we incorporate the META-learning rationale into SMGO -Δ, a global optimization approach recently proposed in the literature. Through a benchmark numerical example we show the practical benefits of our META -extension of the baseline algorithm, while providing theoretical bounds on its performance.

UR - https://www.scopus.com/pages/publications/85184804971

U2 - 10.1109/CDC49753.2023.10383592

DO - 10.1109/CDC49753.2023.10383592

M3 - Conference contribution

AN - SCOPUS:85184804971

SP - 1294

EP - 1299

BT - 2023 62nd IEEE Conference on Decision and Control, CDC 2023

PB - Institute of Electrical and Electronics Engineers

Y2 - 13 December 2023 through 15 December 2023

ER -

META-SMGO-Δ: Similarity as a Prior in Black-Box Optimization

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this