The sorting operation is one of the most commonly used building blocks in computer
programming. In machine learning, it is often used for robust statistics. However, seen as a …

Applications of optimal transport have recently gained remarkable attention as a result of the
computational advantages of entropic regularization. However, in most situations the …

Leverage score sampling provides an appealing way to perform approximate com-putations
for large matrices. Indeed, it allows to derive faithful approximations with a complexity …

Abstract Machine learning models---including prominent zero-shot models---are often
trained on datasets whose labels are only a small proportion of a larger label space. Such …

Annotating datasets is one of the main costs in nowadays supervised learning. The goal of
weak supervision is to enable models to learn using only forms of labelling which are …

We propose and analyze a novel theoretical and algorithmic framework for structured
prediction. While so far the term has referred to discrete output spaces, here we consider …

We propose and analyse a reduced-rank method for solving least-squares regression
problems with infinite dimensional output. We derive learning bounds for our method, and …

Abstract Machine learning approached through supervised learning requires expensive
annotation of data. This motivates weakly supervised learning, where data are annotated …

The branch-and-bound (B&B) procedure is one of the most widely used techniques to get
optimal solutions for the resource-constrained project scheduling problem (RCPSP) …

The expense of acquiring labels in large-scale statistical machine learning makes partially
and weakly-labeled data attractive, though it is not always apparent how to leverage such …