New directions in learning theory

Monday, July 20, 2015 - 11:00am
CS 1240

Speaker Name: 

Prof. Avrim Blum

Speaker Institution: 




Cookies Location: 

CS 1240


The classic PAC-learning model focuses on the problem of learning a single unknown function, over data drawn from a distribution that is unrelated to what is being learned, and that resides on a single machine. A number of current directions in machine learning differ from this setting in crucial ways. These include distributed learning, multi-task learning, semi-supervised learning, and deep/representation learning. This talk will survey some theoretical results in these directions and a number of open algorithmic problems that these directions bring.