A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class Classification
arXiv:2402.08676v15 citationsh-index: 9ISIT
Originality Incremental advance
AI Analysis
This work addresses a theoretical bottleneck in applying AMP to multi-class classification, offering incremental improvements in analysis.
The paper tackles the convergence analysis of approximate message passing (AMP) with non-separable multivariate nonlinearities, providing a complete analysis for a convex optimization problem in multi-class classification.
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.