Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled
data to mitigate the reliance on large labeled datasets. In this work, we unify the current …

Deep learning is usually described as an experiment-driven field under continuous criticizes
of lacking theoretical foundations. This problem has been partially fixed by a large volume of …

We show that parametric models trained by a stochastic gradient method (SGM) with few
iterations have vanishing generalization error. We prove our results by arguing that SGM is …

Differential privacy is an essential and prevalent privacy model that has been widely
explored in recent decades. This survey provides a comprehensive and structured overview …

Adaptivity is an important feature of data analysis-the choice of questions to ask about a
dataset often depends on previous interactions with the same dataset. However, statistical …

Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to
understanding this problem focus on statistical inference and generalization of individual …

We establish novel generalization bounds for learning algorithms that converge to global
minima. We derive black-box stability results that only depend on the convergence of a …

Machine learning models in health care are often deployed in settings where it is important
to protect patient privacy. In such settings, methods for differentially private (DP) learning …

There is a significant conceptual gap between legal and mathematical thinking around data
privacy. The effect is uncertainty as to which technical offerings meet legal standards. This …

How can we select the best performing data-driven model? How can we rigorously estimate
its generalization error? Statistical Learning Theory (SLT) answers these questions by …