John’s theorem proved in 1948 states that any centrally-symmetric convex body in R^d can be sandwiched by two ellipsoids up to a factor of sqrt{d}. In particular, it implies that any d-dimensional normed space embeds…
Recent discussion in the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups. We consider several of the…
The learnability of different neural architectures can be characterized directly by computable measures of data complexity. In this talk, we reframe the problem of architecture selection as understanding how data determines the most expressive and…
Dense Associative Memories are generalizations of Hopfield nets to higher order (higher than quadratic) interactions between the spins/neurons. I will describe a relationship between these models and neural networks commonly used in deep learning. From…
Earlier this week Microsoft Research Montreal celebrated the International Day of Women and Girls in STEM (science, technology, engineering and mathematics) with a one-day symposium: I Chose STEM. More than 200 Canadian STEM students and…
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…
