DCLGNEOct 5, 2022

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

arXiv:2210.04626v11 citationsh-index: 23
Originality Synthesis-oriented
AI Analysis

This work addresses convergence issues in asynchronous algorithms for optimization and machine learning, but it appears incremental as it builds on existing concepts like macroiteration sequences.

The paper tackles the challenge of ensuring convergence in parallel or distributed asynchronous iterative algorithms with features like unbounded delays and flexible communication, particularly for convex optimization and machine learning, by introducing a new convergence result based on the macroiteration sequence concept.

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 macroiteration 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes