Simple Models for Systemsy Problems

Tuesday, October 13, 2026, 11 a.m.

Bahen Centre for Information Technology, BA 3200

This lecture is open to the public. Please register using the link below.

Abstract:

It's 2026, and the answer to every performance, security, or optimization problem is "machine learning." But what kinds of models are appropriate for these applications? In this talk, Margo Seltzer is going to try to convince the audience that, as in good system design, "simpler is better." And, in this case, simpler has many benefits: simpler models are typically more efficient in both space and time, they are frequently transparently interpretable, and in many domains, they produce accuracy and generalization equivalent to the fanciest deep learning model that can be built. 

At the same time, Seltzer is going to explain what great collaboration looks like, how it can help people overcome imposter syndrome, and how it helps them find their own personal superpower. 

Bio:

Margo Seltzer is Canada 150 Research Chair in Computer Systems and the Cheriton Family chair in Computer Science at the University of British Columbia. Her research interests are in systems, construed quite broadly: systems for capturing and accessing data provenance, file systems, databases, transaction processing systems, storage and analysis of graph-structured data, and systems for constructing optimal and interpretable machine learning models. 

She was a co-founder and CTO of Sleepycat Software, the makers of Berkeley DB, the recipient of the 2021 ACM Software Systems award and the 2020 ACM SIGMOD Systems Award.  She is a member of the Royal Society of Canada, the National Academy of Engineering and the American Academy of Arts and Sciences.