Learning algorithms with performance guarantees through data-structural/distributional assumptions, unsupervised learning, language models (including topic models and word embeddings), matrix and tensor factorization, deep nets, sparse coding.
Efficient optimization algorithms for machine learning, non-generative unsupervised and semi-supervised learning, online convex optimization and regret minimization in games.
We welcome Prof. Yoram Singer, who joins us from Google Research Mountain View. He is a world leader in applying optimization to machine learning, who has had great impact on theory and practice.