Jean-Baptiste Fest – Optimization Online

Convergence Analysis of Block Majorize-Minimize Subspace Approaches

Published: 2021/12/06, Updated: 2022/02/05

Applications - Science and Engineering, Unconstrained Optimization block alternating optimization, majorization-minimization, memory gradient methods, non-convex optimization

Majorization-Minimization (MM) consists of a class of efficient and effective optimization algorithms that benefit from solid theoretical foundations. MM methods have shown their great ability to tackle efficiently challenging optimization problems from signal processing, image processing, inverse problems and machine learning. When processing large amount of data/variable, as it may happen in 3D image processing, … Read more

SABRINA: A Stochastic Subspace Majorization-Minimization Algorithm

Published: 2021/08/31, Updated: 2022/05/11

Jean-Baptiste Fest

Émilie Chouzenoux

Convex Optimization, Nonlinear Optimization binary logistic regression, convergence analysis, image reconstruction, majorization-minimization, stochastic optimization, subspace acceleration

A wide class of problems involves the minimization of a coercive and differentiable function $F$ on $\mathbb{R}^N$ whose gradient cannot be evaluated in an exact manner. In such context, many existing convergence results from standard gradient-based optimization literature cannot be directly applied and robustness to errors in the gradient is not necessarily guaranteed. This work … Read more