A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to 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.

View graph Source

Paper

Similar papers

A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class ClassificationBurak Çakmak, Yue Lu, Manfred Opper2024 In Library

Mixed Regression via Approximate Message PassingNelvin Tan, R. Venkataramanan2023 · Journal of machine learning research · 9 citations In Library

Building Conformal Prediction Intervals with Approximate Message PassingLucas Clarté, Lenka Zdeborová2024 · arXiv (Cornell University) · 2 citations In Library

Convergence of Some Convex Message Passing Algorithms to a Fixed PointVáclav Voráček, Tomáš Werner2024 · International Conference on Machine Learning · 0 citations In Library

Alternating Constrained Minimization Based Approximate Message PassingC. Thomas, D. Slock2023 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 1 citation In Library

Multiprocessor approximate message passing with column-wise partitioningYanting Ma, Yue M. Lu, D. Baron2017 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 4 citations In Library

Convolutional Approximate Message-PassingK. Takeuchi2020 · IEEE Signal Processing Letters · 26 citations In Library

Multi-Environment GLAMP: Approximate Message Passing for Transfer Learning with Applications to Lasso-based EstimatorsLonglin Wang, Yanke Song, Kuanhao Jiang et al.2025 · 0 citations In Library

Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message PassingR. Venkataramanan, Kevin Kögler, Marco Mondelli2021 · International Conference on Machine Learning · 36 citations In Library

Bayes-Optimal Convolutional AMPK. Takeuchi2021 · International Symposium on Information Theory · 1 citation In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal