Salvato in:
Dettagli Bibliografici
Autori principali: Jia, Zhihao, Pang, Qi, Tran, Trung, Woodruff, David, Zhang, Zhihao, Zheng, Wenting
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.03132
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913637189287936
author Jia, Zhihao
Pang, Qi
Tran, Trung
Woodruff, David
Zhang, Zhihao
Zheng, Wenting
author_facet Jia, Zhihao
Pang, Qi
Tran, Trung
Woodruff, David
Zhang, Zhihao
Zheng, Wenting
contents In this work, we study the experts problem in the distributed setting where an expert's cost needs to be aggregated across multiple servers. Our study considers various communication models such as the message-passing model and the broadcast model, along with multiple aggregation functions, such as summing and taking the $\ell_p$ norm of an expert's cost across servers. We propose the first communication-efficient protocols that achieve near-optimal regret in these settings, even against a strong adversary who can choose the inputs adaptively. Additionally, we give a conditional lower bound showing that the communication of our protocols is nearly optimal. Finally, we implement our protocols and demonstrate empirical savings on the HPO-B benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03132
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Communication Bounds for the Distributed Experts Problem
Jia, Zhihao
Pang, Qi
Tran, Trung
Woodruff, David
Zhang, Zhihao
Zheng, Wenting
Machine Learning
In this work, we study the experts problem in the distributed setting where an expert's cost needs to be aggregated across multiple servers. Our study considers various communication models such as the message-passing model and the broadcast model, along with multiple aggregation functions, such as summing and taking the $\ell_p$ norm of an expert's cost across servers. We propose the first communication-efficient protocols that achieve near-optimal regret in these settings, even against a strong adversary who can choose the inputs adaptively. Additionally, we give a conditional lower bound showing that the communication of our protocols is nearly optimal. Finally, we implement our protocols and demonstrate empirical savings on the HPO-B benchmarks.
title Communication Bounds for the Distributed Experts Problem
topic Machine Learning
url https://arxiv.org/abs/2501.03132