Kirill Struminsky

The Deep Weight Prior - a Prior Distribution for CNNs via Generative Modeling of Parameters of the Model

Dmitry Vetrov, Max Welling, Andrei Atanov, 2018 .

A Simple Method to Evaluate Support Size and Non-uniformity of a Decoder-Based Generative Model

Dmitry P. Vetrov, Kirill Struminsky, 2019, AIST.

Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution pdf

Novi Quadrianto, Dmitry Vetrov, Kirill Struminsky, 2019, AAAI.

Robust Variational Inference pdf

Dmitry P. Vetrov, Michael Figurnov, Kirill Struminsky, 2016, ArXiv.

The Deep Weight Prior. Modeling a prior distribution for CNNs using generative models pdf

Max Welling, Dmitry P. Vetrov, Andrei Atanov, 2018, ArXiv.

The Deep Weight Prior

Max Welling, Dmitry Vetrov, Andrei Atanov, 2018, ICLR.

A new approach for sparse Bayesian channel estimation in SCMA uplink systems

Dmitry P. Vetrov, Ivan V. Oseledets, Kirill Struminsky, 2016, 2016 8th International Conference on Wireless Communications & Signal Processing (WCSP).

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

Anton Osokin, Kirill Struminsky, Simon Lacoste-Julien, 2018, NeurIPS.

Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces pdf

Dmitry Vetrov, Kirill Struminsky, Artyom Gadetsky, 2021, NeurIPS.