paper-with-me

Papers

Distributed TD(0) with Almost No Communication

2023-05-25 · Rui Liu, Alex Olshevsky

We provide a new non-asymptotic analysis of distributed temporal difference learning with linear function approximation. Our approach relies on ``one-shot averaging,'' where $N$ agents run identical local copies of the TD(0) method and average the outcomes only once at the very end. We demonstrate a version of the linear time speedup phenomenon, where the convergence time of the distributed process is a factor of $N$ faster than the convergence time of TD(0). This is the first result proving benefits from parallelism for temporal difference methods.

📄 PDF Abstract BibTeX arXiv:2305.16246

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Distributed Inference with Sparse and Quantized Communication

2020-04-02 · Aritra Mitra, John A. Richards, Saurabh Bagchi, Shreyas Sundaram

We consider the problem of distributed inference where agents in a network observe a stream of private signals generated by an unknown state, and aim to uniquely identify this state from a finite set of hypotheses. We fo…

Quantization

Signal-Comparison-Based Distributed Estimation Under Decaying Average Data Rate Communications

2024-05-29 · Jieming Ke, Xiaodong Lu, Yanlong Zhao, Ji-Feng Zhang

The paper investigates the distributed estimation problem under low bit rate communications. Based on the signal-comparison (SC) consensus protocol under binary-valued communications, a new consensus+innovations type dis…

Event-Triggered Distributed Estimation With Decaying Communication Rate

2021-03-10 · Xingkang He, Yu Xing, Junfeng Wu, Karl H. Johansson

We study distributed estimation of a high-dimensional static parameter vector through a group of sensors whose communication network is modeled by a fixed directed graph. Different from existing time-triggered communicat…

Communication-Efficient Projection-Free Algorithm for Distributed Optimization

2018-05-20 · Yan Li, Chao Qu, Huan Xu

Distributed optimization has gained a surge of interest in recent years. In this paper we propose a distributed projection free algorithm named Distributed Conditional Gradient Sliding(DCGS). Compared to the state-of-the…

Distributed OptimizationMatrix Completion

Quantized Epoch-SGD for Communication-Efficient Distributed Learning

2019-01-10 · Shen-Yi Zhao, Hao Gao, Wu-Jun Li

Due to its efficiency and ease to implement, stochastic gradient descent (SGD) has been widely used in machine learning. In particular, SGD is one of the most popular optimization methods for distributed learning. Recent…

Quantization