Curriculum vitae

Short Research Statement. Through a unifying framework, with the power of continuous relaxations (beyond convexity) and primal-dual certificates (using Karush-Kuhn-Tucker conditions), my research group produces novel algorithms for learning and inference in combinatorial problems. Our aim is to generate correct, computationally efficient and statistically efficient algorithms for high dimensional machine learning problems. Our results pertain not only to classical worst-case NP-hard problems, such as learning and inference in structured prediction, community detection and learning Bayesian networks, but also to areas of recent interest such as fairness, meta learning and federated learning.