Bayesian statistics is an approach to data analysis based on Bayes' theorem, where
available knowledge about parameters in a statistical model is updated with the information …

Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of
challenging problems. However, since deep learning methods operate as black boxes, the …

An Introduction to Variational Autoencoders Page 1 An Introduction to Variational Autoencoders
Page 2 Other titles in Foundations and Trends R in Machine Learning Computational Optimal …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

This paper provides a review and commentary on the past, present, and future of numerical
optimization algorithms in the context of machine learning applications. Through case …

Deep learning tools have gained tremendous attention in applied machine learning.
However such tools for regression and classification do not capture model uncertainty. In …

Unsupervised learning of probabilistic models is a central yet challenging problem in
machine learning. Specifically, designing models with tractable learning, sampling …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

The reparameterization trick enables optimizing large scale stochastic computation graphs
via gradient descent. The essence of the trick is to refactor each stochastic node into a …

Deep learning describes a class of machine learning algorithms that are capable of
combining raw inputs into layers of intermediate features. These algorithms have recently …