A fundamental challenge for machine learning models is generalizing to out-of-distribution
(OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize …

Despite remarkable success in a variety of applications, it is well-known that deep learning
can fail catastrophically when presented with out-of-distribution data. Toward addressing …

Federated Learning (FL) has emerged as the tool of choice for training deep models over
heterogeneous and decentralized datasets. As a reflection of the experiences from different …

The goal of continual learning is to find a model that solves multiple learning tasks which are
presented sequentially to the learner. A key challenge in this setting is that the learner may" …

We consider the pool-based active learning problem, where only a subset of the training
data is labeled, and the goal is to query a batch of unlabeled samples to be labeled so as to …

Underlying data structures, such as symmetries or invariance to transformations, are often
exploited to improve the solution of learning tasks. However, embedding these properties in …

When deploying machine learning solutions, they must satisfy multiple requirements beyond
accuracy, such as fairness, robustness, or safety. These requirements are imposed during …

In this work, we solve the problem of novel category detection under distribution shift. This
problem is critical to ensuring the safety and efficacy of machine learning models …

With the widespread adoption of machine learning systems, the need to curtail their
behavior has become increasingly apparent. This is evidenced by recent advancements …

Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a
truncated iterative algorithm in the layers of a trainable neural network. However, the …