paper-with-me

Papers

Gap-Dependent Bounds for Federated $Q$-learning

2025-02-05 · Haochen Zhang, Zhong Zheng, Lingzhou Xue

We present the first gap-dependent analysis of regret and communication cost for on-policy federated $Q$-Learning in tabular episodic finite-horizon Markov decision processes (MDPs). Existing FRL methods focus on worst-case scenarios, leading to $\sqrt{T}$-type regret bounds and communication cost bounds with a $\log T$ term scaling with the number of agents $M$, states $S$, and actions $A$, where $T$ is the average total number of steps per agent. In contrast, our novel framework leverages the benign structures of MDPs, such as a strictly positive suboptimality gap, to achieve a $\log T$-type regret bound and a refined communication cost bound that disentangles exploration and exploitation. Our gap-dependent regret bound reveals a distinct multi-agent speedup pattern, and our gap-dependent communication cost bound removes the dependence on $MSA$ from the $\log T$ term. Notably, our gap-dependent communication cost bound also yields a better global switching cost when $M=1$, removing $SA$ from the $\log T$ term.

📄 PDF Abstract BibTeX arXiv:2502.02859

Code (0)

등록된 구현이 없습니다.

Tasks

Q-Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

On the Necessity of Collaboration for Online Model Selection with Decentralized Data

2024-04-15 · Junfan Li, Zheshun Wu, Zenglin Xu, Irwin King

We consider online model selection with decentralized data over $M$ clients, and study the necessity of collaboration among clients. Previous work proposed various federated algorithms without demonstrating their necessi…

Model Selection

Optimal Federated Learning for Functional Mean Estimation under Heterogeneous Privacy Constraints

2024-12-25 · Tony Cai, Abhinav Chakraborty, Lasse Vuursteen

Federated learning (FL) is a distributed machine learning technique designed to preserve data privacy and security, and it has gained significant importance due to its broad range of applications. This paper addresses th…

Federated LearningPrivacy Preserving

Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels

2021-02-05 · NeurIPS 2021 12 · Hao Wang, Rui Gao, Flavio P. Calmon

Machine learning models trained by different optimization algorithms under different data distributions can exhibit distinct generalization behaviors. In this paper, we analyze the generalization of models trained by noi…

Federated LearningGeneralization BoundsLearning Theory

Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles

2023-07-10 · Kevin Scaman, Mathieu Even, Batiste Le Bars, Laurent Massoulié

In this paper, our aim is to analyse the generalization capabilities of first-order methods for statistical learning in multiple, different yet related, scenarios including supervised learning, transfer learning, robust …

Federated Learningparameter estimationQuantizationTransfer Learning

Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning

2022-02-04 · L. P. Barnes, Alex Dytso, H. V. Poor

We consider information-theoretic bounds on expected generalization error for statistical learning problems in a networked setting. In this setting, there are $K$ nodes, each with its own independent dataset, and the mod…

Federated LearningGeneralization Bounds