Assistant Professor, Department of Statistics, Columbia University
Prof. Samory Kpotufe is an Assistant Professor, Department of Statistics, Columbia University, and was previously an assistant professor at Princeton university. His main practical aim is to design adaptive procedures, i.e., practical procedures that can self-tune to unknown structure in data (e.g., manifold, sparsity, clusters), while at the same time meeting the various constraints (e.g., time, space, labelling cost) of modern applications. He works generally in machine learning, with an emphasis on nonparametric methods and high-dimensional statistics.
Samory recently won the first prize in the 2018 Bell Labs Prize, and $100,000, for his pioneering work on the critically important field of ‘transfer learning’ in machine learning that answers the question of how and when can learning from one machine learning tool, be applied to another; this is a question that lies at the heart of all machine learning – is each model a ‘one off’ or can the learnings be applied to other scenarios, and if so when? Samory has answered this question with a breakthrough theory that provides a quantitative answer.