no code implementations • 6 Mar 2024 • Nazar Buzun, Maksim Bobrin, Dmitry V. Dylov
We present a new extension for Neural Optimal Transport (NOT) training procedure, capable of accurately and efficiently estimating optimal transportation plan via specific regularisation on conjugate potentials.
no code implementations • 20 Feb 2024 • Maksim Bobrin, Nazar Buzun, Dmitrii Krylov, Dmitry V. Dylov
We report that AILOT outperforms state-of-the art offline imitation learning algorithms on D4RL benchmarks and improves the performance of other offline RL algorithms in the sparse-reward tasks.
1 code implementation • 27 Jul 2022 • Artyom Sorokin, Nazar Buzun, Leonid Pugachev, Mikhail Burtsev
This requires to store prohibitively large intermediate data if a sequence consists of thousands or even millions elements, and as a result, makes learning of very long-term dependencies infeasible.
no code implementations • 2 Apr 2021 • Iaroslav Bespalov, Nazar Buzun, Oleg Kachan, Dmitry V. Dylov
Oftentimes, these methods either fail to produce enough new data or expand the dataset beyond the original knowledge domain.
no code implementations • 20 Jun 2020 • Iaroslav Bespalov, Nazar Buzun, Dmitry V. Dylov
Unsupervised retrieval of image features is vital for many computer vision tasks where the annotation is missing or scarce.
no code implementations • 7 Feb 2020 • Nikolay Shvetsov, Nazar Buzun, Dmitry V. Dylov
We propose a new unsupervised and non-parametric method to detect change points in intricate quasi-periodic signals.