A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class Classification

2024/02/13 by Burak Çakmak, Yue Lu, Çakmak, Burak +3
Computer Science · #FOS: Computer and information sciences #Face and Expression Recognition #Information Theory (cs.IT) #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2402.08676

openalex publication_date 2024/02/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Motivated by the recent application of approximate message passing (AMP) to the analysis of convex optimizations in multi-class classifications [Loureiro, et. al., 2021], we present a convergence analysis of AMP dynamics with non-separable multivariate nonlinearities. As an application, we present a complete (and independent) analysis of the motivated convex optimization problem.

Related

• Approximate message-passing for convex optimization with non-separable penalties
• Convergence of Message-Passing for Distributed Convex Optimisation with Scaled Diagonal Dominance
• Convergence of Min-Sum Message Passing for Quadratic Optimization
• On Universality of Non-Separable Approximate Message Passing Algorithms
• Convergence of Some Convex Message Passing Algorithms to a Fixed Point