Domain adaptation has become a prominent problem setting in machine learning and
related fields. This review asks the question: How can a classifier learn from a source …

The task of quantification consists in providing an aggregate estimation (eg, the class
distribution in a classification problem) for unseen test sets, applying a model that is trained …

Learning exists in the context of data, yet notions of confidence typically focus on model
predictions, not label quality. Confident learning (CL) is an alternative approach which …

We decompose the evidence lower bound to show the existence of a term measuring the
total correlation between latent variables. We use this to motivate the beta-TCVAE (Total …

To make effective decisions in novel environments with long-horizon goals, it is crucial to
engage in hierarchical reasoning across spatial and temporal scales. This entails planning …

We extend conformal prediction methodology beyond the case of exchangeable data. In
particular, we show that a weighted version of conformal prediction can be used to compute …

Deep generative models provide powerful tools for distributions over complicated manifolds,
such as those of natural images. But many of these methods, including generative …

In many real-world reinforcement learning applications, access to the environment is limited
to a fixed dataset, instead of direct (online) interaction with the environment. When using this …

We consider the off-policy estimation problem of estimating the expected reward of a target
policy using samples collected by a different behavior policy. Importance sampling (IS) has …

Generative adversarial networks (GANs) provide an algorithmic framework for constructing
generative models with several appealing properties: they do not require a likelihood …