Research
In the first part of this talk, I will present recent results on learning image filters for low-level vision. We formulate numerous low-level vision problems (e.g., edge-preserving filtering and denoising) as recursive image filtering via…
Machine learning has become one of the most exciting research areas in the world, with various applications. However, there exists a noticeable gap between theory and practice. On one hand, simple algorithms like stochastic gradient…
Selfish behavior can often lead to a suboptimal outcome for all participants, a phenomenon illustrated by many classical examples in game theory. Over the last decade, we developed a good understanding of how to quantify…
Harness Machine Learning to Improve People’s Lives At Microsoft, we are committed to leveraging the power of Artificial Intelligence (AI) to benefit people and greater society. Advances in AI can be applied to address some…
Quadratic assignment is a very general problem in theoretical computer science. It includes graph matching, the traveling salesman problem, and the Gromov-Hausdorff distance between finite metric spaces as particular cases. Quadratic assignment is in general…
