About me

About me #

I’m an Assistant Professor at the University of Montreal and a Core Academic Member at Mila - Quebec AI Institute developing novel methods in generative modelling, Monte Carlo methods, Optimal Transport, and applying those to solve fundamental problems in natural sciences, e.g. finding eigenstates of the many-body Schrodinger equation, simulating molecular dynamics, predicting the development of biological cells, conformational sampling, and protein folding. Previously, I did two postdocs: at Vector Institute with Alán Aspuru-Guzik and Alireza Makhzani; at the University of Amsterdam with Max Welling.

I was born in Sevastopol, Ukraine, and at the age of 13 I started competing in Ukrainian olympiads on math and physics. Since then I’ve been interested in studying and understanding nature in all its forms from abstract (math, physics, computer science) to practical fields (history, biology, humanities, which I also try to study in my free time).

Regarding the war
I know teachers who organized the Ukrainian Physics Olympiad when I was a kid but now fight for Ukraine with an AR in their hands. Ukraine needs help now more than ever. Here’s a list of organizations where you can make a donation.
Mentoring
I used to devote part of my time to mentoring at Brave Generation. Regardless of your background, don’t hesitate to reach out if you have any questions about research or academia.

Selected Papers #

AI for Science #


  • Doob’s Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling (NeurIPS 2024, spotlight)
    Yuanqi Du, Michael Plainer, Rob Brekelmans, Chenru Duan, Frank Noé, Carla P. Gomes,
    Alan Aspuru-Guzik, Kirill Neklyudov
    arXiv github Open In Colab
  • A Computational Framework for Solving Wasserstein Lagrangian Flows (ICML 2024)
    {Kirill Neklyudov, Rob Brekelmans}*, Alexander Tong, Lazar Atanackovic,
    Qiang Liu, Alireza Makhzani
    arXiv github
  • Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation (NeurIPS 2023, spotlight)
    Kirill Neklyudov, Jannes Nys, Luca Thiede, Juan Carrasquilla, Qiang Liu,
    Max Welling, Alireza Makhzani
    arXiv github
  • Action Matching: Learning Stochastic Dynamics from Samples (ICML 2023)
    Kirill Neklyudov, Rob Brekelmans, Daniel Severo, Alireza Makhzani
    arXiv github Open In Colab

MCMC #


  • Orbital MCMC (AISTATS 2022, oral)
    Kirill Neklyudov, Max Welling
    arXiv github
  • Involutive MCMC: a Unifying Framework (ICML 2020)
    Kirill Neklyudov, Max Welling, Evgenii Egorov, Dmitry Vetrov
    arXiv github
  • Deterministic Gibbs Sampling via ODEs
    Kirill Neklyudov, Roberto Bondesan, Max Welling
    arXiv github
  • The Implicit Metropolis-Hastings Algorithm (NeurIPS 2019)
    Kirill Neklyudov, Evgenii Egorov, Dmitry Vetrov
    arXiv

Bayesian Deep Learning #


  • Variance Networks (ICLR 2019)
    {Kirill Neklyudov, Dmitry Molchanov, Arsenii Ashukha}*, Dmitry Vetrov
    arXiv github
  • Structured Bayesian Pruning (NeurIPS 2017)
    Kirill Neklyudov, Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov
    arXiv github

* (joint main-authorship)

Talks #


Email #


You can find my email in my papers.