Text

Understanding a Class of Decentralized and Federated Optimization Algorithms: A Multirate Feedback Control Perspective

Distributed algorithms have been playing an increasingly important role in many applications such as machine learning, signal processing, and control. Significant research efforts have been devoted to developing and analyzing new algorithms for various applications. In this work, we provide a fresh perspective to understand, analyze, and design distributed optimization algorithms. Through the lens of multirate feedback control, we show that a wide class of distributed algorithms, including popular decentralized/federated schemes, can be viewed as discretizing a certain continuous-time feedback control system, possibly with multiple sampling rates, such as decentralized gradient descent, gradient tracking, and federated averaging. This key observation not only allows us to develop a generic framework to analyze the convergence of the entire algorithm class, but, more importantly, it also leads to an interesting way of designing new distributed algorithms. We develop the theory behind our framework and provide examples to highlight how the framework can be used in practice.

Ketersediaan

Informasi Detail

Judul Seri

SIAM JOURNAL ON OPTIMIZATION; Vol.33 No.2 April-June 2023

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 652-683

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

DISTRIBUTED ALGORITHMS
CONVERGENCE ANALYSIS
CONTROL PERSPECTIVE

Info Detail Spesifik

https://doi.org/10.1137/22M1475648

Pernyataan Tanggungjawab

Xinwei Zhang, Mingyi Hong, Nicola Elia

Versi lain/terkait

Lampiran Berkas

Komentar