12 citations · 22 across the 9 of their papers we have counts for
3 papers · 1 filter
Isotropic Gaussian Processes on Finite Spaces of Graphs
Viacheslav Borovitskiy, Mohammad Reza Karimi, Vignesh Ram Somnath +1
We propose a principled way to define Gaussian process priors on various sets of unweighted graphs: directed or undirected, with or without loops. We endow each of these sets with…
A Dynamical System View of Langevin-Based Non-Convex Sampling
Mohammad Reza Karimi, Ya-Ping Hsieh, Andreas Krause
Non-convex sampling is a key challenge in machine learning, central to non-convex optimization in deep learning as well as to approximate probabilistic inference. Despite its signi…
Riemannian stochastic approximation algorithms
Mohammad Reza Karimi, Ya-Ping Hsieh, Panayotis Mertikopoulos +1
We examine a wide class of stochastic approximation algorithms for solving (stochastic) nonlinear problems on Riemannian manifolds. Such algorithms arise naturally in the study of…