Research Interests: My research focuses on the design and analysis of machine learning algorithms with rigorous guarantees, particularly in supervised, semi-supervised, and adversarial learning. I am also interested in randomized and local-search heuristics for learning, as well as learning from imbalanced and streaming data, both separately and at their intersection.

Across these areas, I seek to establish statistical and computational bounds or computational hardness results, and I complement this theoretical work with careful empirical evaluation when formal guarantees are not available.

During the last couple of years my students and I are investigating semi-supervised learning, regularization methods, learning with streaming data, and related topics.

In the past I have worked on reasoning with knowledge bases and on interpretability of word embeddings. Furthermore, I have also worked on multi-agent protocols and orchestration of multi-agent systems. In the distant past I have also done some work in computer algebra.