Timezone: »

Bottleneck Conditional Density Estimation
Rui Shu · Hung Bui · Mohammad Ghavamzadeh

Mon Aug 07 01:30 AM -- 05:00 AM (PDT) @ Gallery #95

We introduce a new framework for training deep generative models for high-dimensional conditional density estimation. The Bottleneck Conditional Density Estimator (BCDE) is a variant of the conditional variational autoencoder (CVAE) that employs layer(s) of stochastic variables as the bottleneck between the input x and target y, where both are high-dimensional. Crucially, we propose a new hybrid training method that blends the conditional generative model with a joint generative model. Hybrid blending is the key to effective training of the BCDE, which avoids overfitting and provides a novel mechanism for leveraging unlabeled data. We show that our hybrid training procedure enables models to achieve competitive results in the MNIST quadrant prediction task in the fully-supervised setting, and sets new benchmarks in the semi-supervised regime for MNIST, SVHN, and CelebA.

Author Information

Rui Shu (Stanford University)
Hung Bui (Adobe Research)
Mohammad Ghavamzadeh (Adobe Research & INRIA)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors