50 citations · 72 across the 5 of their papers we have counts for
5 papers
Variational Principles for Mirror Descent and Mirror Langevin Dynamics
Belinda Tzen, Anant Raj, Maxim Raginsky +1
Mirror descent, introduced by Nemirovski and Yudin in the 1970s, is a primal-dual convex optimization method that can be tailored to the geometry of the optimization problem at han…
Function approximation by neural nets in the mean-field regime: Entropic regularization and controlled McKean-Vlasov dynamics
Belinda Tzen, Maxim Raginsky
We consider the problem of function approximation by two-layer neural nets with random weights that are "nearly Gaussian" in the sense of Kullback-Leibler divergence. Our setting i…
Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
Belinda Tzen, Maxim Raginsky
In deep latent Gaussian models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlin…
Theoretical guarantees for sampling and inference in generative models with latent diffusions
Belinda Tzen, Maxim Raginsky
We introduce and study a class of probabilistic generative models, where the latent object is a finite-dimensional diffusion process on a finite time interval and the observed vari…
Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability
Belinda Tzen, Tengyuan Liang, Maxim Raginsky
We study the detailed path-wise behavior of the discrete-time Langevin algorithm for non-convex Empirical Risk Minimization (ERM) through the lens of metastability, adopting some t…