Towards a Principled Understanding of Deep Learning

Apply

Project Description

Deep learning models provide state of the art performance on many practical machine learning tasks. However, there is a large gapbetweenour theoretical / conceptual understanding and practice.The intern will work in one of the follow areas, depending on interest and background: - deep learning models- adversarial attacks and robustness- optimization for deep learning- generalization of deep learning- GANs- model compression
Program - Computer Science
Division - Computer, Electrical and Mathematical Sciences and Engineering
Field of Study - ​computer science, mathematics

About the
Researcher

Peter Richtarik

Professor, Computer Science<br/>

Peter Richtarik
Prof. Richtarik's research interests lie at the intersection of mathematics, computer science, machine learning, optimization, numerical linear algebra, high performance computing and applied probability. He is interested in developing zero, first, and second-order algorithms for convex and nonconvex optimization problems described by big data, with a particular focus on randomized, parallel and distributed methods. He is the co-inventor of federated learning, a Google platform for machine learning on mobile devices preserving privacy of users' data.

Desired Project Deliverables

​Ideally contribution to a research paper​.