Research
Developing efficient algorithms that power faster, smarter, and more reliable computing across diverse applications.
Continual learning is the problem faced by intelligent agents of the sort that people and other animals are, that of learning increasingly complex skills and knowledge over time from experience, of becoming increasingly competent over…
Matrix completion is a well-studied problem with many machine learning applications. In practice, the problem is often solved by non-convex optimization algorithms. However, the current theoretical analysis for non-convex algorithms relies heavily on the assumption…
Machine learning (ML) and automatic algorithmic decision making have started to play central and crucial roles in our daily lives. At the same time, more and more data used to train ML algorithms are now…
