Jonathan Wenger

@jwenger.bsky.social

Postdoctoral Research Scientist in Statistics at Columbia University

Probably the best event on probabilistic ML I know 🔥🔥🔥 Highly recommended, especially if you cannot make the UAI deadline (we have a proceedings track published in PMLR!) or are already planning to attend ICML (for example, via the fast track to present an already published paper).

Symposium on Probabilistic Machine Learning@probml.bsky.social · 6mo ago

ProbML 2026 (formerly AABI) invites submissions on probabilistic ML (both Bayesian and otherwise!), July 5 in Seoul (co-located with ICML). Website: probml.cc. Tracks: proceedings (PMLR), workshop, fast track. New focus includes applications in healthcare and climate! Submit by: 20 March 2026.

Submit your work on Probabilistic Machine Learning to @probml.bsky.social and come join us in Seoul (co-located with ICML) this year!

Symposium on Probabilistic Machine Learning@probml.bsky.social · 6mo ago

ProbML 2026 (formerly AABI) invites submissions on probabilistic ML (both Bayesian and otherwise!), July 5 in Seoul (co-located with ICML). Website: probml.cc. Tracks: proceedings (PMLR), workshop, fast track. New focus includes applications in healthcare and climate! Submit by: 20 March 2026.

We've extended the deadline to May 26th, so fear not if your NeurIPS submission still needs attention. You can still submit to our @icmlconf.bsky.social workshop on open-source in Machine Learning!

Frank Schneider@fsschneider.bsky.social · last yr.

Tired of your open-source ML work not getting the academic recognition it deserves? 🤔 Submit to the first-ever CodeML workshop at #ICML2025! It focuses on new libraries, improvements to established ones, best practices, retrospectives, and more. codeml-workshop.github.io/codeml2025/

This has been a topic close to my heart for a long time. We have an awesome lineup of speakers who have made deep contributions to open-source in ML, e.g. @sarahooker.bsky.social , @chrisrackauckas.bsky.social, Matt Johnson, Tri Dao, @stellaathena.bsky.social, Evan Shelhamer.

Frank Schneider@fsschneider.bsky.social · last yr.

Tired of your open-source ML work not getting the academic recognition it deserves? 🤔 Submit to the first-ever CodeML workshop at #ICML2025! It focuses on new libraries, improvements to established ones, best practices, retrospectives, and more. codeml-workshop.github.io/codeml2025/

Finally compiled and refined this a bit; do take a look if you're curious! A more TeX'd version is attached in the screenshots. hackmd.io/@sp-monte-ca... 'Some Intuition Boosters'

BildBildBildBild
Sam Power@spmontecarlo.bsky.social · 2y ago

I was reminded of this thread - x.com/sp_monte_car... - today, and which I will try to refine into a blog post in due course. I originally took a gently-paced screen recording of the thread to post here, but it exceeded the one-minute limit. It might be interesting to do some narrated version.

Optimal transport computes an interpolation between two distributions using an optimal coupling. Flow matching, on the other hand, uses a simpler “independent” coupling, which is the product of the marginals.