Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits

被引：0

作者：

Karpov, Nikolai ^{[1
]}

Zhang, Qin ^{[1
]}

机构：

[1] Indiana Univ, Bloomington, IN 47405 USA

来源：

THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 12 | 2024年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we study the collaborative learning model, which concerns the tradeoff between parallelism and communication overhead in multi-agent multi-armed bandits. For regret minimization in multi-armed bandits, we present the first set of tradeoffs between the number of rounds of communication among the agents and the regret of the collaborative learning process.

引用

页码：13076 / 13084

页数：9

共 50 条

[1] Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits
Li, Tan
Song, Linqi
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2022, 40 (03) : 773 - 787
[2] Constrained regret minimization for multi-criterion multi-armed bandits
Kagrecha, Anmol
Nair, Jayakrishnan
Jagannathan, Krishna
MACHINE LEARNING, 2023, 112 (02) : 431 - 458
[3] Constrained regret minimization for multi-criterion multi-armed bandits
Anmol Kagrecha
Jayakrishnan Nair
Krishna Jagannathan
Machine Learning, 2023, 112 : 431 - 458
[4] Lenient Regret for Multi-Armed Bandits
Merlis, Nadav
Mannor, Shie
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 8950 - 8957
[5] Fairness and Welfare Quantification for Regret in Multi-Armed Bandits
Barman, Siddharth
Khan, Arindam
Maiti, Arnab
Sawarni, Ayush
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 6, 2023, : 6762 - 6769
[6] Bounded Regret for Finitely Parameterized Multi-Armed Bandits
Panaganti, Kishan
Kalathil, Dileep
IEEE CONTROL SYSTEMS LETTERS, 2021, 5 (03): : 1073 - 1078
[7] Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
Bar-On, Yogev
Mansour, Yishay
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[8] Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
Chen, Tianrui
Gangrade, Aditya
Saligrama, Venkatesh
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[9] Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
Chawla, Ronshee
Vial, Daniel
Shakkottai, Sanjay
Srikant, R.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202
[10] Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory
Chaudhuri, Arghya Roy
Kalyanakrishnan, Shivaram
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 10085 - 10092

← 1 2 3 4 5 →