8 citations · 20 across the 11 of their papers we have counts for
12 papers
Deep Multivariate Models with Parametric Conditionals
Dmitrij Schlesinger, Boris Flach, Alexander Shekhovtsov
We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentation…
Game-theoretic distributed learning of generative models for heterogeneous data collections
Dmitrij Schlesinger, Boris Flach
One of the main challenges in distributed learning arises from the difficulty of handling heterogeneous local models and data. In light of the recent success of generative models,…
Symmetric Equilibrium Learning of VAEs
Boris Flach, Dmitrij Schlesinger, Alexander Shekhovtsov
We view variational autoencoders (VAE) as decoder-encoder pairs, which map distributions in the data space to distributions in the latent space and vice versa. The standard learnin…
VAE Approximation Error: ELBO and Exponential Families
Alexander Shekhovtsov, Dmitrij Schlesinger, Boris Flach
The importance of Variational Autoencoders reaches far beyond standalone generative models -- the approach is also used for learning latent representations and can be generalized t…
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
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. We consider stochasti…
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…