Yorgos

I have cleaned up the notebooks for my course on Optimal Transport for Machine Learners and added links to the slides and lecture notes. github.com/gpeyre/ot4ml

CAR Causal Abstractions and RepresentationsWorkshop @ UAI 2025July 25th 2025, Rio de Janeiro 🇧🇷

🔥 Got a great work on causal representation learning, abstraction, high-dimensional discovery, or other hot topics in causality?

🇧🇷 Don’t miss your chance to present in Rio at the CAR Workshop at #UAI2025!

⏰ Deadline is in 1 week – May 26!
🌐 sites.google.com/view/car-25/

If it were an episode of Friends, it would be: The one where Causal Abstractions (finally) meet Causal Representation Learning!

Speakers and CFP are out!

See you in Rio🌴
#UAI #causality #workshop

A great joint work with Gabriele D' Acunto, Fabio Zennaro and Paolo Di Lorenzo!🙏

Hot off the press!💥
arxiv.org/abs/2502.00407

Efficient Event-based Delay Learning in Spiking Neural Networks Spiking Neural Networks (SNNs) are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks. Spiking neurons are stateful and intrinsically recur...

New preprint out with @drtnowotny.bsky.social and @neworderofjamie.bsky.social arxiv.org/abs/2501.07331

That might be the most useful @neuripsconf.bsky.social post I've seen btw

Interested in estimating posterior predictives in Bayesian inference? Really want to know if your approximate inference "is working"?
Come to our poster at the NeurIPS BDU workshop on Saturday - see TL;DR below.

State of AI #NeurIPS

It was the first picture I took in Vancouver

See you at #NeurIPS2024! We’ll present two papers:

1) “Interventionally Consistent Surrogates for Complex Simulation Models”. Here, we propose a method for learning causal abstractions (“interventionally consistent surrogates”) of complex simulation models! openreview.net/pdf?id=UtTjg... (1/3)

Huge shoutout to all the collaborators of this fantastic team: Joel Dyer, Nick Bishop, Fabio Zennaro, Ani Calinescu, Theo Damoulas and Michael Wooldridge🙏

If you want to learn more, join us at poster #5004 in West Ballroom A-D on Thursday, December 12th, from 4:30 PM to 7:30 PM!

Interventionally Consistent Surrogates for Complex Simulation Models Large-scale simulation models of complex socio-technical systems provide decision-makers with high-fidelity testbeds in which policy interventions can be evaluated and _what-if_ scenarios explored....

This work leverages Causal Abstraction theory to build causally consistent surrogates for complex simulation models, enabling more efficient policy evaluation and decision-making.

Paper: openreview.net/forum?id=UtT...
Blog post: www.nickbishop.net/2024/11/02/i...

Next week will be ✈️to @neuripsconf.bsky.social together with @joelnmdyer.bsky.social and Nick Bishop to present our work on "Interventionally Consistent Surrogates for Complex Simulation Models". Details 👇

This work leverages Causal Abstraction theory to build causally consistent surrogates for complex simulation models, enabling more efficient policy evaluation and decision-making.

Paper: openreview.net/forum?id=UtT...
Blog post: www.nickbishop.net/2024/11/02/i...