GAIA seminar

Géométrie, Apprentissage, Information, Algorithmes

Welcome to the seminars of the GAIA team (Géométrie, Apprentissage, Information, Algorithmes) of GIPSA-lab. The objective of GAIA seminars is to invite, about every two months, well-known researchers in signal processing and machine learning (and more…) to give an introductive seminar on their research field. Everybody is welcome to join, you can subscribe to the mailing list below.

Next seminar

January 6th, 2022, 14h00, It will be online. Subscribe to the mailing list here to receive the connection details if you wish to receive the link..
Gersende Fort (CNRS)
Title: FedEM : Expectation Maximization algorithm for Federated Learning
Abstract: The Expectation Maximization (EM) algorithm is an iterative procedure designed to optimize positive functions defined by an integral. EM is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations. To our best knowledge, EM designed for federated learning (FL) is an open question. The goal of this talk is to propose new EM methods designed for FL. First, we will describe the usual EM algorithm in the so-called framework 'complete data model from the exponential family' and how it is related to the Stochastic Approximation methods: EM iterations consist in updating conditional expectations of sufficient statistics; the limiting points of EM are the roots of a function which, in the FL setting, has a specific expression which calls for the use of Stochastic Approximation algorithms. Then, we will introduce and comment two new EM algorithms for FL: the steps made by the local agents, the ones by the central server, how the communication cost agents-server can be controlled, how the possible partial participation of agents is managed. The second EM algorithm includes a variance reduction technique. Finite-time horizon complexity bounds will be commented: what they imply about the role of design parameters on the computational cost of the E-steps, the computational cost of the M-steps, and the communication cost. Numerical examples will illustrate our findings. This is a joint work with Aymeric Dieuleveut (CMAP, Ecole Polytechnique), Eric Moulines (CMAP, Ecole Polytechnique) and Geneviève Robin (LAMME, CNRS); published in the Proceedings of NeurIPS 2021.

May 19th, 2022, 14h00, TBA.
Pierre Weiss (CNRS)
Title: TBA
Abstract: TBA

Mailing list

To receive informations about the seminars (especially for virtual seminars during the COVID-19 pandemic), subscribe to the mailing list here.


Contact [at] gipsa-lab.grenoble-inp [dot] fr