2019-2020 Seminars

To connect to the CSDM Seminar via Zoom, please do the following:
1 - If you have Zoom installed on your device, enter the following meeting ID: 360043913 , click Join Meeting.
2 - If you do not have Zoom installed, click the following link to...

To connect to the CSDM Seminar via Zoom, please do the following: 1 - If you have Zoom installed on your device, enter the following meeting ID: 360043913 , click Join Meeting. 2 - If you do not have Zoom installed, click the following link to...

We study sequential probabilistic prediction on data sequences which are not i.i.d., and even potentially generated by an adversary. At each round, the player assigns a probability distribution to possible outcomes and incurs the log-likelihood of...

In this talk, I will discuss my two recent works on Energy-Based Models. In the first work, I discuss how we can reinterpret standard classification architectures as class conditional energy-based models and train them using recently proposed...

High dimensional expansion generalizes edge and spectral expansion in graphs to hypergraphs (viewed as higher dimensional simplicial complexes). It is a tool that allows analysis of PCP agreement rests, mixing of Markov chains, and construction...

Machine Learning is invaluable for extracting insights from large volumes of data. A key assumption enabling many methods, however, is having access to training data comprising independent observations from the entire distribution of relevant...

Deep neural networks have recently seen an impressive comeback with applications both in the public sector and the sciences. However, despite their outstanding success, a comprehensive theoretical foundation of deep neural networks is still missing...

I’ll discuss the Noisy Quadratic Model, the toy problem of minimizing a convex quadratic function with noisy gradient observations. While the NQM is simple enough to have closed-form dynamics for a variety of optimizers, it gives a surprising amount...