This monograph covers some recent advances in a range of acceleration techniques
frequently used in convex optimization. We first use quadratic optimization problems to …

We address the problem of automatically learning the main steps to complete a certain task,
such as changing a car tire, from a set of narrated instruction videos. The contributions of this …

Building useful predictive models often involves learning from sensitive data. Training
models with differential privacy can guarantee the privacy of such sensitive data. For convex …

We give a simple proof that the Frank-Wolfe algorithm obtains a stationary point at a rate of $
O (1/\sqrt {t}) $ on non-convex objectives with a Lipschitz continuous gradient. Our analysis …

Classical optimal transport problem seeks a transportation map that preserves the total mass
between two probability distributions, requiring their masses to be equal. This may be too …

In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be
a very effective approach. Yet, relying solely on a single detector is also a major limitation …

Maximising a cumulative reward function that is Markov and stationary, ie, defined over state-
action pairs and independent of time, is sufficient to capture many kinds of goals in a Markov …

Abstract The Frank-Wolfe optimization algorithm has recently regained popularity for
machine learning applications due to its projection-free property and its ability to handle …

Over the past decades, numerous loss functions have been been proposed for a variety of
supervised learning tasks, including regression, classification, ranking, and more generally …

Coherent uncertainty quantification is a key strength of Bayesian methods. But modern
algorithms for approximate Bayesian posterior inference often sacrifice accurate posterior …