Markov Chain Monte Carlo methods for sampling from complex distributions...
Policy regularization methods such as maximum entropy regularization are...
We extend temporal-difference (TD) learning in order to obtain
risk-sens...
Many common machine learning methods involve the geometric annealing pat...
The exponential family is well known in machine learning and statistical...
Annealed importance sampling (AIS) is the gold standard for estimating
p...
Achieving the full promise of the Thermodynamic Variational Objective (T...
The recently proposed Thermodynamic Variational Objective (TVO) leverage...
Supervised machine learning models often associate irrelevant nuisance
f...
Compression is at the heart of effective representation learning. Howeve...
Representations of data that are invariant to changes in specified nuisa...
Advances in unsupervised learning enable reconstruction and generation o...