Rafal Jozefowicz — accepted AI-conference papers

2016

Improved Variational Inference with Inverse Autoregressive Flow

Diederik P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, Max Welling

NeurIPS 2016poster

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent sp…

Cited by 2328 Source ↗PDF ↗code ↗Scholar ↗

2015

An Empirical Exploration of Recurrent Network Architectures

Rafal Jozefowicz, Wojciech Zaremba, Ilya Sutskever

ICML 2015poster

The Recurrent Neural Network (RNN) is an extremely powerful sequence model that is often difficult to train. The Long Short-Term Memory (LSTM) is a specific RNN architecture whose design makes it much easier to train. While wildly successful in practice, the LSTM’s architecture appears to be ad-hoc…

Cited by 2562 Source ↗PDF ↗Scholar ↗