activity
20162026
most citedAn efficient Averaged Stochastic Gauss-Newton algorithm for estimating parameters of non linear regressions models

8 citations · 10 across the 14 of their papers we have counts for

collaborators

22 papers

math.ST2026

Complexity reduction in online stochastic Newton methods with potential O(N d) total cost

Antoine Godichon-Baggioni, Bruno Portier, Guillaume Sallé

Optimizing smooth convex functions in stochastic settings, where only noisy estimates of gradients and Hessians are available, is a fundamental problem in optimization. While first…

math.ST2026

Convergence of Multi-Level Markov Chain Monte Carlo Adaptive Stochastic Gradient Algorithms

Antoine Godichon-Baggioni, Gabriel Lang, Sylvain Le Corff +2

Stochastic optimization in learning and inference often relies on Markov chain Monte Carlo (MCMC) to approximate gradients when exact computation is intractable. However, finite-ti…

stat.ML2024

Theoretical Convergence Guarantees for Variational Autoencoders

Sobihan Surendran, Antoine Godichon-Baggioni, Sylvain Le Corff

Variational Autoencoders (VAE) are popular generative models used to sample from complex data distributions. Despite their empirical success in various machine learning tasks, sign…

stat.ML2024

Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization

Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard +1

Optimal Transport (OT) based distances are powerful tools for machine learning to compare probability measures and manipulate them using OT maps. In this field, a setting of intere…

math.ST2024

A Full Adagrad algorithm with O(Nd) operations

Antoine Godichon-Baggioni, Wei Lu, Bruno Portier

A novel approach is given to overcome the computational challenges of the full-matrix Adaptive Gradient algorithm (Full AdaGrad) in stochastic optimization. By developing a recursi…

stat.ML2024

Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation

Sobihan Surendran, Antoine Godichon-Baggioni, Adeline Fermanian +1

Stochastic Gradient Descent (SGD) with adaptive steps is widely used to train deep neural networks and generative models. Most theoretical results assume that it is possible to obt…