Artyom Gadetsky

I am 2nd year PhD student at MLBio lab, EPFL in Lausanne, supervised by Maria Brbic. Currently, I am working on unsupervised transfer and representation learning. Previously, I was a researcher at CS HSE and BayesGroup supervised by Dmitry Vetrov, working 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 real-life problems.

Email  /  CV  /  Google Scholar  /  Github  /  Twitter  /  LinkedIn

profile photo
Research
Let Go of Your Labels with Unsupervised Transfer
Artyom Gadetsky*, Yulun Jiang*, Maria Brbic
poster on ICML 2024
project page / arxiv / code / bibtex / poster

An approach to perform fully unsupervised transfer on a downstream dataset given representation spaces of foundation models. Although being fully unsupervised, our approach outperforms CLIP zero-shot transfer and sometimes matches optimal supervised performance!

Fine-grained Classes and How to Find Them
Matej Grcic*, Artyom Gadetsky*, Maria Brbic
poster on ICML 2024
project page / arxiv / code / bibtex / poster

We develop the approach to infer fine-grained labels given coarsely labeled dataset.

The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning
Artyom Gadetsky, Maria Brbic
spotlight on NeurIPS 2023
project page / arxiv / code / bibtex /
NeurIPS slides / poster

Simple model-agnostic framework for inferring human labeling of a given dataset without any external supervision.

Leveraging Recursive Gumbel-Max 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, top-k).

Low-variance Black-box Gradient Estimates for the Plackett-Luce 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.


This guy makes a nice webpage.