Work

On Parallel or Distributed Asynchronous Iterations with Unbounded Delays and Possible Out of Order Messages or Flexible Communication for Convex Optimization Problems and Machine Learning

Year: 2022

Type: conference-paper

Abstract: We describe several features of parallel or distributed asynchronous iterative algorithms such as unbounded delays, possible out of order messages or flexible communication. We concentrate on the concept of macro-iteration sequence which was introduced in order to study the convergence or termination of asynchronous iterations. A survey of asynchronous iterations for convex optimization problems is also presented. Finally, a new result of convergence for parallel or distributed asynchronous iterative algorithms with flexible communication for convex optimization problems and machine learning is proposed.

Source: IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)

DOI: 10.1109/ipdpsw55747.2022.00135

Author: Didier El-Baz

Institutions: Centre National de la Recherche Scientifique, Laboratoire d'Analyse et d'Architecture des Systèmes

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: Centre International de Mathématiques et d'Informatique (de Toulouse)