Distributionally Robust Optimization via Ball Oracle Acceleration

Yair Carmon; Danielle Hausler

Distributionally Robust Optimization via Ball Oracle Acceleration

Yair Carmon, Danielle Hausler

School of Computer Science

Tel Aviv University

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

4 Scopus citations

Abstract

We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded fdivergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with N non-smooth loss functions, the resulting algorithms find an ε-accurate solution with Õ(Nε^-2/3 + ε^-2) first-order oracle queries to individual loss functions.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
Editors	S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
Publisher	Neural information processing systems foundation
ISBN (Electronic)	9781713871088
State	Published - 2022
Event	36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans, United States Duration: 28 Nov 2022 → 9 Dec 2022

Publication series

Name	Advances in Neural Information Processing Systems
Volume	35
ISSN (Print)	1049-5258

Conference

Conference	36th Conference on Neural Information Processing Systems, NeurIPS 2022
Country/Territory	United States
City	New Orleans
Period	28/11/22 → 9/12/22

Funding

Funders	Funder number
Achelis Foundation
Blavatnik Family Foundation
Israel Science Foundation	2486/21

Cite this

Carmon, Y., & Hausler, D. (2022). Distributionally Robust Optimization via Ball Oracle Acceleration. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022 (Advances in Neural Information Processing Systems; Vol. 35). Neural information processing systems foundation.

Carmon, Yair ; Hausler, Danielle. / Distributionally Robust Optimization via Ball Oracle Acceleration. Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022. editor / S. Koyejo ; S. Mohamed ; A. Agarwal ; D. Belgrave ; K. Cho ; A. Oh. Neural information processing systems foundation, 2022. (Advances in Neural Information Processing Systems).

@inproceedings{284aed5ee5f24e56a6e6601d1b1f0143,

title = "Distributionally Robust Optimization via Ball Oracle Acceleration",

abstract = "We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded fdivergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with N non-smooth loss functions, the resulting algorithms find an ε-accurate solution with {\~O}(Nε-2/3 + ε-2) first-order oracle queries to individual loss functions.",

author = "Yair Carmon and Danielle Hausler",

note = "Publisher Copyright: {\textcopyright} 2022 Neural information processing systems foundation. All rights reserved.; 36th Conference on Neural Information Processing Systems, NeurIPS 2022 ; Conference date: 28-11-2022 Through 09-12-2022",

year = "2022",

language = "אנגלית",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

editor = "S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh",

booktitle = "Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022",

}

Carmon, Y & Hausler, D 2022, Distributionally Robust Optimization via Ball Oracle Acceleration. in S Koyejo, S Mohamed, A Agarwal, D Belgrave, K Cho & A Oh (eds), Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022. Advances in Neural Information Processing Systems, vol. 35, Neural information processing systems foundation, 36th Conference on Neural Information Processing Systems, NeurIPS 2022, New Orleans, United States, 28/11/22.

Distributionally Robust Optimization via Ball Oracle Acceleration. / Carmon, Yair; Hausler, Danielle.
Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022. ed. / S. Koyejo; S. Mohamed; A. Agarwal; D. Belgrave; K. Cho; A. Oh. Neural information processing systems foundation, 2022. (Advances in Neural Information Processing Systems; Vol. 35).

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

TY - GEN

T1 - Distributionally Robust Optimization via Ball Oracle Acceleration

AU - Carmon, Yair

AU - Hausler, Danielle

PY - 2022

Y1 - 2022

N2 - We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded fdivergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with N non-smooth loss functions, the resulting algorithms find an ε-accurate solution with Õ(Nε-2/3 + ε-2) first-order oracle queries to individual loss functions.

AB - We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded fdivergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with N non-smooth loss functions, the resulting algorithms find an ε-accurate solution with Õ(Nε-2/3 + ε-2) first-order oracle queries to individual loss functions.

UR - http://www.scopus.com/inward/record.url?scp=85162742430&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85162742430

T3 - Advances in Neural Information Processing Systems

BT - Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022

A2 - Koyejo, S.

A2 - Mohamed, S.

A2 - Agarwal, A.

A2 - Belgrave, D.

A2 - Cho, K.

A2 - Oh, A.

PB - Neural information processing systems foundation

T2 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022

Y2 - 28 November 2022 through 9 December 2022

ER -

Carmon Y, Hausler D. Distributionally Robust Optimization via Ball Oracle Acceleration. In Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A, editors, Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022. Neural information processing systems foundation. 2022. (Advances in Neural Information Processing Systems).

Distributionally Robust Optimization via Ball Oracle Acceleration

Abstract

Publication series

Conference

Funding

Other files and links

Fingerprint

Cite this