1 citations · 1 across the 3 of their papers we have counts for
4 papers
Quadratic number of nodes is sufficient to learn a dataset via gradient descent
Biswarup Das, Eugene. A. Golikov
We prove that if an activation function satisfies some mild conditions and number of neurons in a two-layered fully connected neural network with this activation function is beyond…
An Essay on Optimization Mystery of Deep Learning
Eugene Golikov
Despite the huge empirical success of deep learning, theoretical understanding of neural networks learning process is still lacking. This is the reason, why some of its features se…
Embedding-reparameterization procedure for manifold-valued latent variables in generative models
Eugene Golikov, Maksim Kretov
Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution. Recent works demonstrated that choice of prior distribution affects learning capacity of VAE model…
Using stochastic computation graphs formalism for optimization of sequence-to-sequence model
Eugene Golikov, Vlad Zhukov, Maksim Kretov
Variety of machine learning problems can be formulated as an optimization task for some (surrogate) loss function. Calculation of loss function can be viewed in terms of stochastic…