Embedding-reparameterization procedure for manifold-valued latent variables in generative models

Autor:	Golikov, Eugene, Kretov, Maksim
Rok vydání:	2018
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution. Recent works demonstrated that choice of prior distribution affects learning capacity of VAE models. We propose a general technique (embedding-reparameterization procedure, or ER) for introducing arbitrary manifold-valued variables in VAE model. We compare our technique with a conventional VAE on a toy benchmark problem. This is work in progress. Comment: Presented at Bayesian Deep Learning workshop (NeurIPS 2018)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1812.02769 Zobrazit plný text záznamu View this record from Arxiv