Dima is going on an internship so I'll be organizing tea talks for the next couple of months!

Abstract: Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech. We propose a novel sequential latent variable model unifying successful ideas from recently proposed architectures: each step in the sequence is associated with a latent variable that is used to condition the recurrent dynamics for future steps. Training is performed with amortised variational inference where the approximate posterior is augmented with a RNN that runs backward through the sequence. In addition to maximizing the variational lower bound, we ease training of the latent variables by adding an auxiliary cost which forces them to reconstruct the state of the backward recurrent network. This provides the latent variables with a task-independent objective that enhances the performance of the overall model. Although being conceptually simple, our model achieves state-of-the-art results on standard speech benchmarks such as TIMIT and BLIZZARD and competitive performance on sequential MNIST. Finally, we apply our model on language modeling in the IMDB dataset. The auxiliary cost is crucial for learning interpretable latent variables.

Michael