Optimization Algorithms for Distributed Machine Learning

Gauri Joshi

ISBN 10: 3031190661 / ISBN 13: 9783031190667

Published by Springer International Publishing, Springer Nature Switzerland Nov 2022, 2022

About this Item

This item is printed on demand - it takes 3-4 days longer - Neuware -This book discusses state-of-the-art stochastic optimization algorithms for distributed machine learning and analyzes their convergence speed. The book first introduces stochastic gradient descent (SGD) and its distributed version, synchronous SGD, where the task of computing gradients is divided across several worker nodes. The author discusses several algorithms that improve the scalability and communication efficiency of synchronous SGD, such as asynchronous SGD, local-update SGD, quantized and sparsified SGD, and decentralized SGD. For each of these algorithms, the book analyzes its error versus iterations convergence, and the runtime spent per iteration. The author shows that each of these strategies to reduce communication or synchronization delays encounters a fundamental trade-off between error and runtime. 144 pp. Englisch.

Seller Inventory # 9783031190667

Bibliographic Details

• Title: Optimization Algorithms for Distributed Machine Learning
• Publisher: Springer International Publishing, Springer Nature Switzerland Nov 2022
• Publication Date: 2022
• Language: English
• ISBN 10: 3031190661
• ISBN 13: 9783031190667
• Binding: Buch
• Condition: Neu
• Dimensions: 246W x 173H x 14D millimeters 246 millimeters width by 173 millimeters height by 14 millimeters depth
• Weight: 430 grams

About this title

Synopsis

This book discusses state-of-the-art stochastic optimization algorithms for distributed machine learning and analyzes their convergence speed. The book first introduces stochastic gradient descent (SGD) and its distributed version, synchronous SGD, where the task of computing gradients is divided across several worker nodes. The author discusses several algorithms that improve the scalability and communication efficiency of synchronous SGD, such as asynchronous SGD, local-update SGD, quantized and sparsified SGD, and decentralized SGD. For each of these algorithms, the book analyzes its error versus iterations convergence, and the runtime spent per iteration. The author shows that each of these strategies to reduce communication or synchronization delays encounters a fundamental trade-off between error and runtime.

About the Author

Gauri Joshi, Ph.D., is an Associate Professor in the ECE department at Carnegie Mellon University. Dr. Joshi completed her Ph.D. from MIT EECS. Her current research is on designing algorithms for federated learning, distributed optimization, and parallel computing. Her awards and honors include being named as one of MIT Technology Review's 35 Innovators under 35 (2022), the NSF CAREER Award (2021), the ACM SIGMETRICS Best Paper Award (2020), Best Thesis Prize in Computer science at MIT (2012), and Institute Gold Medal of IIT Bombay (2010).