Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality

Teodor V. Marinov; Mehryar Mohri; Julian Zimmert

Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality

Teodor V. Marinov, Mehryar Mohri, Julian Zimmert

Computer Science

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

Abstract

We revisit the problem of stochastic online learning with feedback graphs, with the goal of devising algorithms that are optimal, up to constants, both asymptotically and in finite time. We show that, surprisingly, the notion of optimal finite-time regret is not a uniquely defined property in this context and that, in general, it is decoupled from the asymptotic rate. We discuss alternative choices and propose a notion of finite-time optimality that we argue is meaningful. For that notion, we give an algorithm that admits quasi-optimal regret both in finite-time and asymptotically.

Original language	English (US)
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: Nov 28 2022 → Dec 9 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	11/28/22 → 12/9/22

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

Marinov, T. V., Mohri, M., & Zimmert, J. (2022). Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality. 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.

Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality. / Marinov, Teodor V.; Mohri, Mehryar; Zimmert, Julian.
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

Marinov, TV, Mohri, M & Zimmert, J 2022, Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality. 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, 11/28/22.

Marinov TV, Mohri M, Zimmert J. Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality. 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).

Marinov, Teodor V. ; Mohri, Mehryar ; Zimmert, Julian. / Stochastic Online Learning with Feedback Graphs : Finite-Time and Asymptotic Optimality. 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{6c61f9a2869f4fbfa5844644818bfab9,

title = "Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality",

abstract = "We revisit the problem of stochastic online learning with feedback graphs, with the goal of devising algorithms that are optimal, up to constants, both asymptotically and in finite time. We show that, surprisingly, the notion of optimal finite-time regret is not a uniquely defined property in this context and that, in general, it is decoupled from the asymptotic rate. We discuss alternative choices and propose a notion of finite-time optimality that we argue is meaningful. For that notion, we give an algorithm that admits quasi-optimal regret both in finite-time and asymptotically.",

author = "Marinov, {Teodor V.} and Mehryar Mohri and Julian Zimmert",

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 = "English (US)",

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",

}

TY - GEN

T1 - Stochastic Online Learning with Feedback Graphs

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

AU - Marinov, Teodor V.

AU - Mohri, Mehryar

AU - Zimmert, Julian

PY - 2022

Y1 - 2022

N2 - We revisit the problem of stochastic online learning with feedback graphs, with the goal of devising algorithms that are optimal, up to constants, both asymptotically and in finite time. We show that, surprisingly, the notion of optimal finite-time regret is not a uniquely defined property in this context and that, in general, it is decoupled from the asymptotic rate. We discuss alternative choices and propose a notion of finite-time optimality that we argue is meaningful. For that notion, we give an algorithm that admits quasi-optimal regret both in finite-time and asymptotically.

AB - We revisit the problem of stochastic online learning with feedback graphs, with the goal of devising algorithms that are optimal, up to constants, both asymptotically and in finite time. We show that, surprisingly, the notion of optimal finite-time regret is not a uniquely defined property in this context and that, in general, it is decoupled from the asymptotic rate. We discuss alternative choices and propose a notion of finite-time optimality that we argue is meaningful. For that notion, we give an algorithm that admits quasi-optimal regret both in finite-time and asymptotically.

UR - http://www.scopus.com/inward/record.url?scp=85140355250&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85140355250&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85140355250

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

Y2 - 28 November 2022 through 9 December 2022

ER -

Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this