A modern introduction to online learning

F Orabona - arxiv preprint arxiv:1912.13213, 2019 - arxiv.org
In this monograph, I introduce the basic concepts of Online Learning through a modern view
of Online Convex Optimization. Here, online learning refers to the framework of regret …

Tuning-free maximum likelihood training of latent variable models via coin betting

L Sharrock, D Dodd, C Nemeth - … Conference on Artificial …, 2024 - proceedings.mlr.press
We introduce two new particle-based algorithms for learning latent variable models via
marginal maximum likelihood estimation, including one which is entirely tuning-free. Our …

Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds

D Dodd, L Sharrock, C Nemeth - arxiv preprint arxiv:2406.02296, 2024 - arxiv.org
In recent years, interest in gradient-based optimization over Riemannian manifolds has
surged. However, a significant challenge lies in the reliance on hyperparameters, especially …

Mirror and Preconditioned Gradient Descent in Wasserstein Space

C Bonet, T Uscidda, A David… - arxiv preprint arxiv …, 2024 - arxiv.org
As the problem of minimizing functionals on the Wasserstein space encompasses many
applications in machine learning, different optimization algorithms on $\mathbb {R}^ d …

Constrained Sampling with Primal-Dual Langevin Monte Carlo

LFO Chamon, MR Karimi, A Korba - arxiv preprint arxiv:2411.00568, 2024 - arxiv.org
This work considers the problem of sampling from a probability distribution known up to a
normalization constant while satisfying a set of statistical constraints specified by the …