HOME / PUBLICATIONS /

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

Citation:

B. Cakmak, Y. M. Lu, and M. Opper, “A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class Classification,” IEEE International Symposium on Information Theory (ISIT). 2024.

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.

arXiv:2402.08676 [cs.LG]