We present a review of methods for optimal experimental design (OED) for Bayesian inverse
problems governed by partial differential equations with infinite-dimensional parameters …

Despite advances in scalable models, the inference tools used for Gaussian processes
(GPs) have yet to fully capitalize on developments in computing hardware. We present an …

We present PYHESSIAN, a new scalable framework that enables fast computation of
Hessian (ie, second-order derivative) information for deep neural networks. PYHESSIAN …

Quantization is an effective method for reducing memory footprint and inference time of
Neural Networks. However, ultra low precision quantization could lead to significant …

Training neural ODEs on large datasets has not been tractable due to the necessity of
allowing the adaptive numerical ODE solver to refine its step size to very small values. In …

Recently, flat minima are proven to be effective for improving generalization and sharpness-
aware minimization (SAM) achieves state-of-the-art performance. Yet the current definition of …

Recent advances in commonsense reasoning depend on large-scale human-annotated
training data to achieve peak performance. However, manual curation of training examples …

Presently the most successful approaches to semi-supervised learning are based on
consistency regularization, whereby a model is trained to be robust to small perturbations of …

Existing disentanglement methods for deep generative models rely on hand-picked priors
and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a …

Network quantization aims at reducing bit-widths of weights and/or activations, particularly
important for implementing deep neural networks with limited hardware resources. Most …