Events - November 2023

Please note: This PhD defence will take place in DC 2314 and online.

Johra Muhammad Moosa, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Bin Ma

Please note: This seminar will take place in M3 4206 and online.

Rachel Yun Zhang, PhD student
CSAIL, Massachusetts Institute of Technology

A code, which is a set of strings called codewords, is locally testable if one can test whether a given word is close to a codeword by reading only a few bits. Locally testable codes have been studied since the 1990s as key ingredients in the construction of probabilistically checkable proofs.

Please note: This seminar will take place in MC 5501 and online.

Mika Göös, Assistant Professor
Theory Group, École polytechnique fédérale de Lausanne

We present a top-down lower-bound method for depth-4 Boolean circuits. In particular, we give a new proof of the well-known result that the parity function requires depth-4 circuits of size exponential in n^{1/3}. Our proof is an application of robust sunflowers and block unpredictability.

Joint with Artur Riazanov, Anastasia Sofronova, and Dmitry Sokolov.

Please note: This seminar will take place in DC 1304 and online.

Han Zhao, Assistant Professor
Computer Science, University of Illinois Urbana-Champaign
Amazon Visiting Academic, Amazon AI and Search Science

To mitigate the bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance. Understanding such tradeoffs, therefore, underlies the design of optimal and fair algorithms.

Please note: This PhD seminar will take place in DC 2564 and online.

Farshad Kazemi, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Shane McIntosh

Please note: This seminar will take place in DC 1304.

Marina Meila
Department of Statistics, University of Washington
Senior Fellow, University of Washington’s eScience Institute

Please note: The PhD seminar will take place in DC 2310 and online.

Dihong Jiang, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Yaoliang Yu, Sun Sun

Please note: This PhD seminar will take place online.

Shaokai Wang, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Bin Ma

Please note: This seminar will take place in M3 4206 and online.

Harold Nieuwboer, PhD student
Korteweg-de Vries Institute and QuSoft
University of Amsterdam

Please note: This PhD seminar will take place online.

Marvin Pafla, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Kate Larson, Mark Hancock

With the rise of large language models (LLMs) like GPT, the field of eXplainable artificial intelligence (XAI) has exploded and produced a plethora of methods  (e.g., saliency-maps) to gain insight into deep neural nets. However, human-participant studies question the efficacy of these methods, particularly when the AI output is wrong.

Please note: This PhD defence will take place in DC 2310 and virtually.

Glaucia Melo dos Santos, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Paulo Alencar, Daniel Berry, Donald Cowan

Please note: This workshop will take place in DC 1302 and online.

You are invited to join the Machine Learning Theory Workshop on Monday, November 6, 2023 in DC 1302 and online. 

This workshop will bring together researchers with expertise in mathematical foundations of machine learning. The purpose of this event is to foster connections and build a research community among learning theorists from various institutions.