Previous Special Year Seminar

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...

Causal inference from observational data is a vital problem, but it comes with strong assumptions. Most methods require that we observe all confounders, variables that affect both the causal variables and the outcome variables. But whether we have...

Function approximators, like deep neural networks, play a crucial role in building machine-learning based intelligent systems. This talk covers three core problems of function approximators: understanding function approximators, designing new...

Online learning is a popular framework for sequential prediction problems. The standard approach to analyzing an algorithm's (learner's) performance in online learning is in terms of its empirical regret defined to be the excess loss suffered by the...

We make the case that over the coming decade, computer assisted reasoning will become far more widely used in the mathematical sciences. This includes interactive and automatic theorem verification, symbolic algebra, and emerging technologies such...

The classical regression problem seeks to estimate a function f on the basis of independent pairs $(x_i,y_i)$ where $\mathbb E[y_i]=f(x_i)$, $i=1,\dotsc,n$. In this talk, we consider statistical and computational aspects of the "uncoupled" version...

This talk focuses on a general phenomenon of "Frequency-Principle" that DNNs often fit target functions from low to high frequencies during the training. I will present empirical evidences on real datasets and deep networks of different settings as...

Minimax optimization, especially in its general nonconvex formulation, has found extensive applications in modern machine learning, in settings such as generative adversarial networks (GANs) and adversarial training. It brings a series of unique...