The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …

Learning in the presence of outliers is a fundamental problem in statistics. Until recently, all
known efficient unsupervised learning algorithms were very sensitive to outliers in high …

As data are increasingly being stored in different silos and societies becoming more aware
of data privacy issues, the traditional centralized training of artificial intelligence (AI) models …

As machine learning systems grow in scale, so do their training data requirements, forcing
practitioners to automate and outsource the curation of training data in order to achieve state …

Byzantine resilience emerged as a prominent topic within the distributed machine learning
community. Essentially, the goal is to enhance distributed optimization algorithms, such as …

We study high-dimensional distribution learning in an agnostic setting where an adversary is
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …

We study a recently proposed large-scale distributed learning paradigm, namely Federated
Learning, where the worker machines are end users' own devices. Statistical and …

In high dimensions, most machine learning methods are brittle to even a small fraction of
structured outliers. To address this, we introduce a new meta-algorithm that can take in a …

Abstract Machine learning models trained on data from the outside world can be corrupted
by data poisoning attacks that inject malicious points into the models' training sets. A …

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while
being more scalable for computation and estimation in high dimensions. The goal of this …