Seminar on Theoretical Machine Learning

A common situation in Machine Learning is one where training data is not fully representative of a target population due to bias in the sampling mechanism or high costs in sampling the target population; in such situations, we aim to ’transfer’...

This talk surveys the role of margins in the analysis of deep networks. As a concrete highlight, it sketches a perceptron-based analysis establishing that shallow ReLU networks can achieve small test error even when they are quite narrow, sometimes...

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...

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...

When high-quality labeled training data are unavailable, an alternative is to learn from training sources that are biased in some way. This talk will cover my group’s recent work on three problems where a learner has access to multiple biased...

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...

Linear regression in L_p-norm is a canonical optimization problem that arises in several applications, including sparse recovery, semi-supervised learning, and signal processing. Standard linear regression corresponds to p=2, and p=1 or infinity is...