My research mostly focuses on exploring distributional properties of Bayesian neural networks. More specifically, I am interested in explaining the difference between deep learning models of wide and shallow regimes in order to improve the interpretability and efficiency of the models.
I did my graduate studies in Statify and Thoth teams under supervision of Julyan Arbel and Jakob Verbeek. During November 2019-January 2020, I was visiting Duke University and working on prior predictive distributions in BNNs under supervision of David Dunson. Prior to that, I obtained my Bachelor degree at Moscow Institute of Physics and Technology (MIPT) and did the second year of Master program at Grenoble Institute of Technology (Grenoble - INP, Ensimag).
My CV can be found here.
Hobbies: travelling, hiking and playing the ukulele.
22 June-1 July 2022
24 June 2022 I got a best poster award at BaYSM (Montreal, Canada).
25-29 April 2022 I am invited to give a talk on Bayesian deep learning at BNP Networking Workshop (Nicosia, Cyprus).
22 June-1 July 2022 I am organizing a session on Bayesian deep learning at ISBA'22 World Meeting (Montreal, Canada).
2 December 2021: I will give a talk on Bayesian deep learning at AI seminar series in ImVia (Dijon, France).
2 November 2021: our paper "Dependence between Bayesian neural network units" is accepted to NeurIPS workshop on Bayesian deep learning (BDL)!
11 Septemter 2021: our paper "Bayesian neural network unit priors and generalized Weibull-tail property" is accepted to ACML 2021! [arXiv]