The deep weight prior. modeling a prior distribution for cnns using generative models A Atanov, A Ashukha, K Struminsky, D Vetrov, M Welling arXiv preprint arXiv:1810.06943, 2018 | 44 | 2018 |
A new approach for sparse Bayesian channel estimation in SCMA uplink systems K Struminsky, S Kruglik, D Vetrov, I Oseledets 2016 8th International Conference on Wireless Communications & Signal …, 2016 | 17 | 2016 |
Low-variance black-box gradient estimates for the plackett-luce distribution A Gadetsky, K Struminsky, C Robinson, N Quadrianto, D Vetrov Proceedings of the AAAI Conference on Artificial Intelligence 34 (06), 10126 …, 2020 | 12 | 2020 |
Leveraging recursive gumbel-max trick for approximate inference in combinatorial spaces K Struminsky, A Gadetsky, D Rakitin, D Karpushkin, DP Vetrov Advances in Neural Information Processing Systems 34, 10999-11011, 2021 | 9 | 2021 |
Well log data standardization, imputation and anomaly detection using hidden Markov models K Struminskiy, A Klenitskiy, A Reshytko, D Egorov, A Shchepetnov, ... Petroleum Geostatistics 2019 2019 (1), 1-5, 2019 | 6 | 2019 |
Differentiable rendering with reparameterized volume sampling N Morozov, D Rakitin, O Desheulin, D Vetrov, K Struminsky arXiv preprint arXiv:2302.10970, 2023 | 4 | 2023 |
Quantifying learning guarantees for convex but inconsistent surrogates K Struminsky, S Lacoste-Julien, A Osokin Advances in Neural Information Processing Systems 31, 2018 | 4 | 2018 |
Устойчивый к шуму метод обучения вариационного автокодировщика МВ Фигурнов, КА Струминский, ДП Ветров | 2 | 2017 |
Robust variational inference M Figurnov, K Struminsky, D Vetrov arXiv preprint arXiv:1611.09226, 2016 | 2 | 2016 |
A Simple Method to Evaluate Support Size and Non-uniformity of a Decoder-Based Generative Model K Struminsky, D Vetrov Analysis of Images, Social Networks and Texts: 8th International Conference …, 2019 | | 2019 |