Exciting stuff: next week at the Online Monte Carlo Seminar, we will finally have a bit of Randomised Numerical Linear Algebra, courtesy of Ethan Epperly (Berkeley). See our website (sites.google.com/view/monte-c...) for details about the talk, taking place next Tuesday (3 February).
Excited for the return of our seminar for another season!
Link with details: sites.google.com/view/monte-c...
See everyone in 2026!
I was in a Zoom meeting when someone called a paper published at NeurIPS 2023 “old.”😅
Very exciting lineup of speakers!
The first talk of the season will be this coming Tuesday (23 September), given by Alexandre Bouchard-Côté from UBC. Alex is a great speaker, so do join if you have the chance!
See sites.google.com/view/monte-c... for details, links, and so on.
Returning soon - stay tuned!
sites.google.com/view/monte-c...
In the interim, I wanted to advertise our YouTube channel - youtube.com/@montecarlos... - which contains recordings for the bulk of our talks so far (sites.google.com/view/monte-c..., sites.google.com/view/monte-c...). I encourage you to catch up and enjoy them over the intervening months!
Starting from last October, we (@OnlineMCSeminar on Twitter, sites.google.com/view/monte-c...) have been running an online seminar on all aspects of Monte Carlo methods, with about ~30 talks so far. We are currently paused for the summer, expecting to return in September 2025.
Yeah, my guess is that generating pretty images does not necessarily require accurate sampling from the original distribution. That said, increasing the number of discretization steps still improves metrics like FID for DDIM.
If you think the process as targeting at p(x) using proposal q(x, x’) = \int_y p(y|x) p(x’|y) dy, then it should have acceptance 1?
A recording of my talk from this afternoon: youtu.be/jSeXZ6IjKn8?...
A touch of self-advertisement: I'll be giving a research talk next Tuesday at the Online Monte Carlo Seminar (sites.google.com/view/monte-c...) on one of my favourite topics: the convergence properties of the Random Walk Metropolis algorithm. Please join us!
Jeremias Knoblauch and other colleagues and friends in UCL launched a "Post-Bayes seminar series". Their will be many blocks of talks, including a series on PAC-Bayes (probably starting in September 2025).
The first talk (by Jeremias) is next week. Please have a look:
postbayes.github.io/seminar/
The recording, for anybody who's interested: youtu.be/FRoia-lszVM?.... Well worth a watch!
Honorable mentions
Can we directly use Ascolani-Lavenant-Zanella on this? I thought their entropy contraction implies spectral gap, spectral gap implies mixing time under warm start.
The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...
Cross-posting this - please join us!
Mailing List link: groups.google.com/g/internatio...
YouTube Channel link: www.youtube.com/@MonteCarloS...
