We show that many machine-learning algorithms are specific instances of a single algorithm
called the Bayesian learning rule. The rule, derived from Bayesian principles, yields a wide …

Classical federated learning (FL) enables training machine learning models without sharing
data for privacy preservation, but heterogeneous data characteristic degrades the …

Sharp global convergence guarantees for iterative nonconvex optimization with random data
Page 1 The Annals of Statistics 2023, Vol. 51, No. 1, 179–210 https://doi.org/10.1214/22-AOS2246 …

Many problems in machine learning can be formulated as optimizing a convex functional
over a vector space of measures. This paper studies the convergence of the mirror descent …

Stochastic Approximation (SA) is a classical algorithm that has had since the early days a
huge impact on signal processing, and nowadays on machine learning, due to the necessity …

Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best
approximation of the posterior distribution within a parametric family, minimizing a loss that …

Abstract The Expectation Maximization (EM) algorithm is the default algorithm for inference
in latent variable models. As in any other field of machine learning, applications of latent …

The Blahut-Arimoto algorithm is a well-known method to compute classical channel
capacities and rate-distortion functions. Recent works have extended this algorithm to …

We consider a general class of regression models with normally distributed covariates, and
the associated nonconvex problem of fitting these models from data. We develop a general …

This paper proposes a general switching dynamical system model, and a custom
majorization-minimization-based algorithm EM++ for identifying its parameters. For certain …