131 citations · 179 across the 26 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Particle Dynamics for Learning EBMs
Kirill Neklyudov, Priyank Jaini, Max Welling
Energy-based modeling is a promising approach to unsupervised learning, which yields many downstream applications from a single model. The main difficulty in learning energy-based…
stat.CO2021★ 2 cited
Deterministic Gibbs Sampling via Ordinary Differential Equations
Kirill Neklyudov, Roberto Bondesan, Max Welling
Deterministic dynamics is an essential part of many MCMC algorithms, e.g. Hybrid Monte Carlo or samplers utilizing normalizing flows. This paper presents a general construction of…