Artyom Gadetsky
I am 1st year Fellowship PhD student at EPFL EDIC. Previously, I was a junior researcher at CS HSE and BayesGroup supervised by Dmitry Vetrov. My last research project was focused on stochastic optimization w.r.t. discrete distributions over structured objects such as graphs, permutations, etc. Generally speaking I am interested in different applications of probabilistic modelling to solve general machine learning problems as well as reallife problems.
Email /
CV /
Google Scholar /
Github /
Twitter /
LinkedIn



Leveraging Recursive GumbelMax Trick for Approximate Inference in Combinatorial Spaces
Kirill Struminsky*,
Artyom Gadetsky*,
Denis Rakitin*,
Danil Karpushkin,
Dmitry Vetrov
poster on NeurIPS 2021
arxiv /
code /
bibtex /
NeurIPS slides /
poster
Tractable discrete distributions and stochastic optimization w.r.t. discrete distributions over structured objects (i.e. graphs, permutations, topk).


Lowvariance Blackbox Gradient Estimates for the PlackettLuce Distribution
Artyom Gadetsky*,
Kirill Struminsky*,
Christopher Robinson,
Novi Quadrianto
Dmitry Vetrov
oral on AAAI 2020
spotlight on BDL NeurIPS 2019 Workshop
arxiv /
code /
bibtex /
AAAI slides /
BDL slides /
poster
Variance reduction techniques for stochastic optimization w.r.t. a distribution over permutations.


Conditional Generators of Words Definitions
Artyom Gadetsky,
Ilya Yakubovskiy,
Dmitry Vetrov
poster on ACL 2018
arxiv /
code /
bibtex /
poster
The generative model for definitions of polysemous words given vector representation of the word and example of its use.

