The world's most prestigious machine learning conference wraps up in Vancouver this weekend. Synced takes a look at the numbers associated with NeurIPS 2019. This year marked the 33rd annual NeurIPS conference. Communication Co-chair Michael Littman told attendees: "This year is only the third time NeurIPS has had a formal relationship with the press. Also, there were 3 awards -- Outstanding Paper, Outstanding New Directions Paper, and Test of Time.
We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training leads to significantly more coherent topics. To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality. Experiments on several real datasets show that our model produces significantly better topics than existing topic models.