Search Results for author: Viktor Yanush

Found 3 papers, 0 papers with code

Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks

no code implementations11 Jun 2020 Alexander Shekhovtsov, Viktor Yanush

Training neural networks with binary weights and activations is a challenging problem due to the lack of gradients and difficulty of optimization over discrete weights.

Variational Inference

Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks

no code implementations NeurIPS 2020 Alexander Shekhovtsov, Viktor Yanush, Boris Flach

In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response.

Hamiltonian Monte-Carlo for Orthogonal Matrices

no code implementations23 Jan 2019 Viktor Yanush, Dmitry Kropotov

In \citet{byrne2013geodesic} authors have already considered sampling from distributions over manifolds using exact geodesic flows in a scheme similar to Hamiltonian Monte Carlo (HMC).

Riemannian optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.