The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …

We show for the first time that learning powerful representations from speech audio alone
followed by fine-tuning on transcribed speech can outperform the best semi-supervised …

We first introduce various algorithms and techniques for machine learning and data science.
While there is a strong focus on neural network applications in unsupervised, supervised …

Categorical variables are a natural choice for representing discrete structure in the world.
However, stochastic neural networks rarely use categorical latent variables due to the …

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 …

Generative flows and diffusion models have been predominantly trained on ordinal data, for
example natural images. This paper introduces two extensions of flows and diffusion for …

Many real-world Internet of Things (IoT) systems, which include a variety of Internet-
connected sensory devices, produce substantial amounts of multivariate time-series data …

Conventional neural architecture search (NAS) approaches are usually based on
reinforcement learning or evolutionary strategy, which take more than 1000 GPU hours to …

We introduce instancewise feature selection as a methodology for model interpretation. Our
method is based on learning a function to extract a subset of features that are most …

Vision transformers (ViTs) have recently received explosive popularity, but their enormous
model sizes and training costs remain daunting. Conventional post-training pruning often …