Apratim Bhattacharyya (PhD Student)

Generative Adversarial Networks (GANs) can achieve state-of-the-art sample
quality in generative modelling tasks but suffer from the mode collapse
problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a
reconstruction-based data log-likelihood forcing it to cover all modes, but
suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN
frameworks which integrate a GAN-based synthetic likelihood to the VAE
objective to address both the mode collapse and sample quality issues, with
limited success. This is because the VAE objective forces a trade-off between
the data log-likelihood and divergence to the latent prior. The synthetic
likelihood ratio term also shows instability during training. We propose a
novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable
direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN
framework to achieve high data log-likelihood and low divergence to the latent
prior at the same time and shows significant improvement over both hybrid
VAE-GANS and plain GANs in mode coverage and quality.

For autonomous agents to successfully operate in the real world, anticipation

of future events and states of their environment is a key competence. This

problem can be formalized as a sequence prediction problem, where a number of

observations are used to predict the sequence into the future. However,

real-world scenarios demand a model of uncertainty of such predictions, as

future states become increasingly uncertain and multi-modal -- in particular on

long time horizons. This makes modelling and learning challenging. We cast

state of the art semantic segmentation and future prediction models based on

deep learning into a Bayesian formulation that in turn allows for a full

Bayesian treatment of the prediction problem. We present a new sampling scheme

for this model that draws from the success of variational autoencoders by

incorporating a recognition network. In the experiments we show that our model

outperforms prior work in accuracy of the predicted segmentation and provides

calibrated probabilities that also better capture the multi-modal aspects of

possible future states of street scenes.

Discovering the key structure of a database is one of the main goals of data

mining. In pattern set mining we do so by discovering a small set of patterns

that together describe the data well. The richer the class of patterns we

consider, and the more powerful our description language, the better we will be

able to summarise the data. In this paper we propose \ourmethod, a novel greedy

MDL-based method for summarising sequential data using rich patterns that are

allowed to interleave. Experiments show \ourmethod is orders of magnitude

faster than the state of the art, results in better models, as well as

discovers meaningful semantics in the form patterns that identify multiple

choices of values.