Pavel Izmailov, PhD candidate
Computer Science Department, New York University
Felix Dangel, Postdoctoral Researcher
Vector Institute for Artificial Intelligence
Popular deep learning frameworks prioritize computing the average mini-batch gradient. Yet, other quantities such as its variance or many approximations to the Hessian can be computed efficiently, and at the same time as the gradient mean. They are of great interest to researchers and practitioners, but implementing them is often burdensome or inefficient.
Anupa Murali, Master’s candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Bin Ma
Niki Hasrati, Master’s candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Shai Ben-David
Matt D’Souza, Master’s candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Ondřej Lhoták
Parametric polymorphism, also known as generics, is an abstraction that lets programmers define code that behaves independently of the types of values it operates on. Generics is a useful abstraction to enable code reuse and improve the maintainability of software projects.
Silvia Sellán, PhD candidate
Department of Computer Science, University of Toronto
Catherine St-Pierre, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Éric Schost
This thesis presents an algorithm to find the local structure of intersections of plane curves.
Tanya Berger-Wolf
Director, Translational Data Analytics Institute
Professor, Computer Science and Engineering | Electrical and Computer Engineering | Evolution, Ecology, and Organismal Biology
Director, Imageomics Institute
Ohio State University
Jelle Hellings, Assistant Professor
Department of Computing and Software, McMaster University
Joseph Musleh, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Éric Schost