← Search

Alican Bozkurt

2 accepted papers

2021

Rate-Regularization and Generalization in Variational Autoencoders

AISTATS 2021poster

Variational autoencoders (VAEs) optimize an objective that comprises a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is often interpreted as a regularizer that controls the degree of compression. We here examine whether inc…

2019

Structured Disentangled Representations

AISTATS 2019poster

Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. Thes…