paper-with-me

Papers

Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

2021-10-04 · Chuanhao Li, Hongning Wang

Linear contextual bandit is a popular online learning problem. It has been mostly studied in centralized learning settings. With the surging demand of large-scale decentralized model learning, e.g., federated learning, how to retain regret minimization while reducing communication cost becomes an open challenge. In this paper, we study linear contextual bandit in a federated learning setting. We propose a general framework with asynchronous model update and communication for a collection of homogeneous clients and heterogeneous clients, respectively. Rigorous theoretical analysis is provided about the regret and communication cost under this distributed learning framework; and extensive empirical evaluations demonstrate the effectiveness of our solution.

📄 PDF Abstract BibTeX arXiv:2110.01463

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Pure Exploration in Asynchronous Federated Bandits

2023-10-17 · Zichen Wang, Chuanhao Li, Chenyu Song, Lianghui Wang 외

We study the federated pure exploration problem of multi-armed bandits and linear bandits, where $M$ agents cooperatively identify the best arm via communicating with the central server. To enhance the robustness against…

Multi-Armed Bandits

Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations

2024-05-11 · Yumeng Shao, Jun Li, Long Shi, Kang Wei 외

Conventional synchronous federated learning (SFL) frameworks suffer from performance degradation in heterogeneous systems due to imbalanced local data size and diverse computing power on the client side. To address this …

Federated LearningModel Selection

Time-triggered Federated Learning over Wireless Networks

2022-04-26 · Xiaokang Zhou, Yansha Deng, Huiyun Xia, Shaochuan Wu 외

The newly emerging federated learning (FL) framework offers a new way to train machine learning models in a privacy-preserving manner. However, traditional FL algorithms are based on an event-triggered aggregation, which…

Federated LearningPrivacy Preserving

Optimizing Asynchronous Federated Learning: A~Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency

2025-02-12 · Abdelkrim Alahyane, Céline Comte, Matthieu Jonckheere, Éric Moulines

Synchronous federated learning (FL) scales poorly with the number of clients due to the straggler effect. Algorithms like FedAsync and GeneralizedFedAsync address this limitation by enabling asynchronous communication be…

Federated Learning

Thompson Sampling for (Combinatorial) Pure Exploration

2022-06-18 · Siwei Wang, Jun Zhu

Existing methods of combinatorial pure exploration mainly focus on the UCB approach. To make the algorithm efficient, they usually use the sum of upper confidence bounds within arm set $S$ to represent the upper confiden…

Thompson Sampling