no code implementations • 13 Feb 2024 • Burak Çakmak, Yue M. Lu, Manfred Opper
Motivated by the recent application of approximate message passing (AMP) to the analysis of convex optimizations in multi-class classifications [Loureiro, et.
no code implementations • 16 Feb 2022 • Burak Çakmak, Yue M. Lu, Manfred Opper
We analyze the dynamics of a random sequential message passing algorithm for approximate inference with large Gaussian latent variable models in a student-teacher scenario.
no code implementations • 5 Jan 2021 • Burak Çakmak, Manfred Opper
We analyze the random sequential dynamics of a message passing algorithm for Ising models with random interactions in the large system limit.
no code implementations • 4 May 2020 • Burak Çakmak, Manfred Opper
We define a message-passing algorithm for computing magnetizations in Restricted Boltzmann machines, which are Ising models on bipartite graphs introduced as neural network models for probability distributions over spin configurations.
no code implementations • 3 Feb 2020 • Manfred Opper, Burak Çakmak
We use freeness assumptions of random matrix theory to analyze the dynamical behavior of inference algorithms for probabilistic models with dense coupling matrices in the limit of large systems.
no code implementations • 14 Jan 2020 • Burak Çakmak, Manfred Opper
We analyze the dynamics of an algorithm for approximate inference with large Gaussian latent variable models in a student-teacher scenario.
no code implementations • 24 Jan 2019 • Burak Çakmak, Manfred Opper
We propose an iterative algorithm for solving the Thouless-Anderson-Palmer (TAP) equations of Ising models with arbitrary rotation invariant (random) coupling matrices.
no code implementations • 16 Jan 2018 • Burak Çakmak, Manfred Opper
We study asymptotic properties of expectation propagation (EP) -- a method for approximate inference originally developed in the field of machine learning.
no code implementations • 23 Aug 2016 • Burak Çakmak, Manfred Opper, Bernard H. Fleury, Ole Winther
Our approach extends the framework of (generalized) approximate message passing -- assumes zero-mean iid entries of the measurement matrix -- to a general class of random matrix ensembles.