Arsenii Ashukha

Samsung (Russia) — Russia

Computer Science · Physical Sciences

10h-index1.6kcitations20works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(7), Adversarial Robustness in Machine Learning(6), Advanced Neural Network Applications(5), Generative Adversarial Networks and Image Synthesis(5), Anomaly Detection Techniques and Applications(5)

Publications20 total

Automating Control of Overestimation Bias for Reinforcement Learning
Research Square (Research Square)·2022· 3 citedOpen Access
Resolution-robust Large Mask Inpainting with Fourier Convolutions
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)·2022· 901 citedOpen Access
Automating Control of Overestimation Bias for Continuous Reinforcement Learning
arXiv (Cornell University)·2021· 3 citedOpen Access
Automating Control of Overestimation Bias for Reinforcement Learning
arXiv (Cornell University)·2021Open Access
Resolution-robust Large Mask Inpainting with Fourier Convolutions
arXiv (Cornell University)·2021· 7 citedOpen Access
Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations
arXiv (Cornell University)·2021· 3 citedOpen Access
Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation
arXiv (Cornell University)·2020· 42 citedOpen Access
Greedy Policy Search: A Simple Baseline for Learnable Test-Time\n Augmentation
arXiv (Cornell University)·2020· 18 citedOpen Access
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
arXiv (Cornell University)·2020· 79 citedOpen Access
Semi-Conditional Normalizing Flows for Semi-Supervised Learning
arXiv (Cornell University)·2019· 22 citedOpen Access
Uncertainty Estimation via Stochastic Batch Normalization
Lecture notes in computer science·2019· 10 citedOpen Access
The Deep Weight Prior
arXiv (Cornell University)·2018· 16 citedOpen Access
The Deep Weight Prior - a Prior Distribution for CNNs via Generative Modeling of Parameters of the Model
arXiv (Cornell University)·2018Open Access
The Deep Weight Prior. Modeling a prior distribution for CNNs using generative models.
arXiv (Cornell University)·2018· 1 citedOpen Access
Variance Networks: When Expectation Does Not Meet Your Expectations
International Conference on Learning Representations·2018· 2 cited
Variance Networks: When Expectation Does Not Meet Your Expectations
arXiv (Cornell University)·2018· 13 citedOpen Access
Bayesian Incremental Learning for Deep Neural Networks
arXiv (Cornell University)·2018· 10 citedOpen Access
Structured Bayesian Pruning via Log-Normal Multiplicative Noise
arXiv (Cornell University)·2017· 68 citedOpen Access
Structured Bayesian Pruning via Log-Normal Multiplicative Noise
Neural Information Processing Systems·2017· 92 cited
Variational Dropout Sparsifies Deep Neural Networks
arXiv (Cornell University)·2017· 347 citedOpen Access

Frequent Co-authors

Dmitry Vetrov(17), Dmitry Molchanov(10), Andrei Atanov(6), Kirill Neklyudov(5), Alexander Lyzhov(3), Kirill Struminsky(3), Max Welling(3), Arsenii Kuznetsov(3), Artem Tsypin(3), Roman Suvorov(2), Elizaveta Logacheva(2), Anton Mashikhin(2), Aleksei Silvestrov(2), Naejin Kong(2), Harshith Goka(2), Kiwoong Park(2), Victor Lempitsky(2), Yuliya Molchanova(2), А. М. Гришин(2), Artur Kadurin(2)