2 citations · 3 across the 5 of their papers we have counts for
6 papers · 1 filter
Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators
Alexander Shekhovtsov
Discrete and especially binary random variables occur in many machine learning models, notably in variational autoencoders with binary latent states and in stochastic binary networ…
MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother +1
Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications. This w…
Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization
Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother +1
We consider the maximum-a-posteriori inference problem in discrete graphical models and study solvers based on the dual block-coordinate ascent rule. We map all existing solvers in…
Stochastic Normalizations as Bayesian Learning
Alexander Shekhovtsov, Boris Flach
In this work we investigate the reasons why Batch Normalization (BN) improves the generalization performance of deep networks. We argue that one major reason, distinguishing it fro…
Normalization of Neural Networks using Analytic Variance Propagation
Alexander Shekhovtsov, Boris Flach
We address the problem of estimating statistics of hidden units in a neural network using a method of analytic moment propagation. These statistics are useful for approximate white…
Generative learning for deep networks
Boris Flach, Alexander Shekhovtsov, Ondrej Fikar
Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional dis…