WebNotice

Please note: This seminar will take place in DC 2585.

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.

Please note: This PhD seminar will take place online.

Joseph Musleh, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Éric Schost

Please note: This PhD seminar will be given online.

David Radke, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Kate Larson, Tim Brecht

While it has long been recognized that a team of individual learning agents can be greater than the sum of its parts, recent work has shown that larger teams are not necessarily more effective than smaller ones.

Please note: This seminar will take place virtually over Zoom.

Pavel Izmailov, PhD candidate
Computer Science Department, New York University

Please note: This seminar will take place in DC 1304 and virtually over Zoom.

Jason Li, Postdoctoral Fellow
Simons Institute, University of California, Berkeley

Please note: This PhD seminar will take place online.

Greg Philbrick, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Craig Kaplan

This paper treats the subject of pseudo-3D modeling (via drawing in projective coordinates). I'll talk about the authors’ methods, as well as my own exploration of pseudo-3D drawing techniques.

Please note: This PhD seminar will take place online.

Xinyu Shi, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Jian Zhao

Please note: This master’s thesis presentation will take place in DC 1304 and virtually.

Benjamin Thérien, Master’s candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Krzysztof Czarnecki

Please note: This seminar will take place in DC 1302.

Roswitha Rissner, Department of Mathematics
Alpen-Adria-Universität Klagenfurt, Austria

Given a square matrix B' over a (commutative) ring S, the null ideal N_0(B') is the ideal consisting of all polynomials f in S[X] for which f(B')=0. In the case that S=R/J is the residue class ring of a ring R modulo an ideal J, we can equivalently study the so-called J-ideals

N_J(B) =  { f in  R[X]  |  f(B) in M_n(J) }

Please note: This PhD defence will take place in DC 1331.

Aida Sheshbolouki, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor M. Tamer Özsu