activity
20172021
most citedDeterministic Gibbs Sampling via Ordinary Differential Equations

2 citations · 3 across the 3 of their papers we have counts for

collaborators

8 papers

stat.CO20212 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…

cs.LG20201 cited

Involutive MCMC: a Unifying Framework

Kirill Neklyudov, Max Welling, Evgenii Egorov +1

Markov Chain Monte Carlo (MCMC) is a computational approach to fundamental problems such as inference, integration, optimization, and simulation. The field has developed a broad sp…

stat.ML2019

The Implicit Metropolis-Hastings Algorithm

Kirill Neklyudov, Evgenii Egorov, Dmitry Vetrov

Recent works propose using the discriminator of a GAN to filter out unrealistic samples of the generator. We generalize these ideas by introducing the implicit Metropolis-Hastings…

cs.LG2019

MaxEntropy Pursuit Variational Inference

Evgenii Egorov, Kirill Neklydov, Ruslan Kostoev +1

One of the core problems in variational inference is a choice of approximate posterior distribution. It is crucial to trade-off between efficient inference with simple families as…

stat.ML2018

Metropolis-Hastings view on variational inference and adversarial training

Kirill Neklyudov, Evgenii Egorov, Pavel Shvechikov +1

A significant part of MCMC methods can be considered as the Metropolis-Hastings (MH) algorithm with different proposal distributions. From this point of view, the problem of constr…

stat.ML2018

Uncertainty Estimation via Stochastic Batch Normalization

Andrei Atanov, Arsenii Ashukha, Dmitry Molchanov +2

In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximaze…