no code implementations • 14 Mar 2023 • Milena Gazdieva, Arip Asadulaev, Alexander Korotin, Evgeny Burnaev
We address this challenge and propose a novel theoretically-justified and lightweight unbalanced EOT solver.
no code implementations • 18 Jul 2022 • Arip Asadulaev, Alexander Panfilov, Andrey Filchenkov
Adversarial examples are transferable between different models.
no code implementations • 18 Jul 2022 • Arip Asadulaev, Alexander Panfilov, Andrey Filchenkov
It was shown that adversarial examples improve object recognition.
no code implementations • 18 Jul 2022 • Rostislav Korst, Arip Asadulaev
We propose the novel framework for generative modelling using hybrid energy-based models.
no code implementations • 30 May 2022 • Arip Asadulaev, Vitaly Shutov, Alexander Korotin, Alexander Panfilov, Andrey Filchenkov
In domain adaptation, the goal is to adapt a classifier trained on the source domain samples to the target domain.
no code implementations • 30 May 2022 • Arip Asadulaev, Alexander Korotin, Vage Egiazarian, Petr Mokrov, Evgeny Burnaev
We introduce a novel neural network-based algorithm to compute optimal transport (OT) plans for general cost functionals.
no code implementations • 29 Sep 2021 • Arip Asadulaev, Vitaly Shutov, Alexander Korotin, Alexander Panfilov, Andrey Filchenkov
In our algorithm, instead of mapping from target to the source domain, optimal transport maps target samples to the set of adversarial examples.
no code implementations • ICLR Workshop EBM 2021 • Arip Asadulaev
The connection of optimal transport and neural networks finds a rich application in machine learning problems.
no code implementations • 23 Oct 2020 • Gideon Stein, Andrey Filchenkov, Arip Asadulaev
To support the findings of this work, this paper seeks to provide an additional example of a Transformer-based RL method.
4 code implementations • ICLR 2021 • Alexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev
We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance).
no code implementations • 5 Aug 2019 • Arip Asadulaev
The problem is that the amount of information is also growing, and many methods remain unknown in a large number of papers.
no code implementations • 13 Jun 2019 • Arip Asadulaev, Igor Kuznetsov, Gideon Stein, Andrey Filchenkov
In this paper, we try to answer the following question: Can information about policy conditioning help to shape a more stable and general policy of reinforcement learning agents?
no code implementations • 13 Jun 2019 • Arip Asadulaev, Igor Kuznetsov, Andrey Filchenkov
It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions.