While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

Missing data is a problem often found in real-world datasets and it can degrade the
performance of most machine learning models. Several deep learning techniques have …

We propose a novel high-performance and interpretable canonical deep tabular data
learning architecture, TabNet. TabNet uses sequential attention to choose which features to …

Multivariate time series with missing values are common in areas such as healthcare and
finance, and have grown in number and complexity over the years. This raises the question …

We consider the problem of handling missing data with deep latent variable models
(DLVMs). First, we present a simple technique to train DLVMs when the training set contains …

Causal inference is essential for data-driven decision making across domains such as
business engagement, medical treatment and policy making. However, research on causal …

Consider the problem of imputing missing values in a dataset. One the one hand,
conventional approaches using iterative imputation benefit from the simplicity and …

Abstract Concept bottleneck models (CBMs) are interpretable neural networks that first
predict labels for human-interpretable concepts relevant to the prediction task, and then …

Feature selection helps reduce data acquisition costs in ML, but the standard approach is to
train models with static feature subsets. Here, we consider the dynamic feature selection …

Bayesian optimal experimental design (BOED) is a principled framework for making efficient
use of limited experimental resources. Unfortunately, its applicability is hampered by the …