3 papers
math.ST2026
Consistency of variational approximations under bounded Kullback--Leibler divergence
Hien Duy Nguyen, Jacob Westerhout, Thomas Guilmeau +1
Variational methods are widely used to approximate posterior distributions in Bayesian inference when exact computation is infeasible. We study when such approximations inherit pos…
stat.ME2026
Convergence of projected stochastic natural gradient variational inference for various step size and sample or batch size schedules
Thomas Guilmeau, Hadrien Hendrikx, Florence Forbes
Stochastic natural gradient variational inference (NGVI) is a popular and efficient algorithm for Bayesian inference. Despite empirical success, the convergence of this method is s…
math.ST2024
Regularized Rényi divergence minimization through Bregman proximal gradient algorithms
Thomas Guilmeau, Emilie Chouzenoux, VÃctor Elvira
We study the variational inference problem of minimizing a regularized Rényi divergence over an exponential family. We propose to solve this problem with a Bregman proximal gradie…