For professors working in the rough AI + Health area, this is a pretty wild opportunity. UBC is one of the top schools in Canada and $1 million per year for 8 years will go far here.

I’m excited to announce that my new book, The Irrational Decision, is available for pre-order from Princeton University Press. press.princeton.edu/books/hardcove…

The CIFAR Deep Learning and RL Summer School gave me 90 minutes to overview optimization for machine learning. Here is is what I used: cs.ubc.ca/~schmidtm/Docu… (The biggest updates are to step sizes and Adam) What are big issues I missed and/or mis-leading things I included?

idk why people say that the VC theory doesn't explain deep learning it looks pretty clear to me that frontier labs managed to figure out generalization under pressure from their VCs

Wow, that could lead to some interesting dynamics.

The rebuttal process NeurIPS Conference was too collegial and productive, so a bunch of papers whose process ended on a positive note will be rejected.

My acceptance speech at the Turing award ceremony: Good evening ladies and gentlemen. The main idea of reinforcement learning is that a machine might discover what to do on its own, without being told, from its own experience, by trial and error. As far as I know, the first

We did a very careful study of 10 optimizers with no horse in the race. Despite all the excitement about Muon, Mars, Kron, Soap, etc., at the end of the day, if you tune the hyperparameters rigorously and scale up, the speedup over AdamW diminishes to only 10% :-( Experiments

An honourable mention for my former PhD student Fred's thesis. His thesis contributions are excellent examples of "thinking outside the box" and how you can complex topics easier to parse by using lots of visualizations: open.library.ubc.ca/media/stream/p…

Another nice contribution to the "out-of-distribution detection does not do what you think it does" canon. This was our exploration of similar ideas in 2018: arxiv.org/abs/1809.04729 (The original name of the paper was "Does Your Model Know the Digit 6 Is Not a Cat?")

This is the way.

100%!

I know and I like a lot of the authors here. But this is pretty funny.

UBC Computer Science invites applications for up to two full-time tenure-track positions with the following priority areas: visualization, robotics, reinforcement learning, data management, and data mining. Applications are due Wed Dec 10, 2025. cs.ubc.ca/our-department…