#ICLR2024 Highlights from the CBL! THIS WEEK, members of the Cambridge Machine Learning Group will be showcasing their work at ICLR 2024! A 🧵on what to expect from our team...

"Stochastic Gradient Descent for Gaussian Processes Done Right" 🎓 Jihao Andreas Lin*, Shreyas Padhy *, Javier Antorán *, Austin Tripp , Alexander Terenin - on the faculty job market, Csaba Szepesvári, Jose Miguel Hernández-Lobato, David Janz 📅 May 10, 9:45 AM 📍 Poster Session 7

Today at ICLR, we're presenting "Stochastic Gradient Descent for Gaussian Processes Done Right". This work uses insights from optimization theory to improve performance of stochastic-gradient-descent based large-scale Gaussian processes training algorithms. More below:

This work was developed jointly with a host of amazing collaborators, including Jihao Andreas Lin, Shreyas Padhy, Javier Antorán, Austin Tripp, Csaba Szepesvari, Jose Miguel Hernández-Lobato, and Dave Janz. The paper can be found here: arxiv.org/abs/2310.20581 Now, let's check out the details!

TLDR: Jihao Andreas Lin continues to make GPs Better, Faster, Stronger. GP-based LLM coming soon. 🤖🤖 We review and analyze best-practices for GP hyper parameter learning which are not given attention in the literature, but when combined, yield orders of magnitude speedups!

Registration for #AABI2024 in 📷Vienna📷 (co-located with ICML) is now open at aabi2024.eventbrite.com !! Spots are free but limited, so get your tickets quick!⏩

YC S24's Ångström AI builds fast and experimentally accurate Gen AI simulations of molecular interactions, replacing wet lab experiments in the drug development pipeline. ycombinator.com/launches/LGp-n… Congraats on the launch, Javier Antorán, Laurence Midgley, and Jose Miguel Hernández-Lobato!

Super stoked to be building accelerated molecular simulations at Ångström AI with Javier Antorán Jose Miguel Hernández-Lobato and Gabor Csanyi! We combine experimentally accurate force fields (MACE) with accelerated sampling using generative models. To start off we are focusing on providing

Going to ICML is ~2 weeks? In Vienna already on Sunday? Why not hang out with probabilistic inference folks? Chat about the future of prob. modeling in the foundation model era, decision-making & planning under uncertainty, and other stuff! Registration is free, but limited 👇

🚀 Ångström AI launched! Replace wetlab experiments with Gen AI molecular simulations "Accelerating molecular simulation using generative AI" ⚡️ 🌐 angstrom-ai.com 🧪 Ångström AI builds fast and experimentally accurate generative AI-based simulations of molecular

Really excited that AABI is sponsored by Basis this year. See you on Sunday!

Excited to kick off the 6th Symposium on Advances in Approximate Bayesian Inference! We will be livestreaming the event here: bit.ly/aabi2024 🚀 Check out the schedule and our many great speakers: approximateinference.org/schedule/index… #ICML2024 AABI

If you can't be in Vienna today to join us for AABI 2024, you can watch our live stream!

Proceedings of the 6th Symposium on Advances in Approximate Bayesian Inference, held in Vienna and co-located with #ICML2024, is now available at proceedings.mlr.press/v253/ #AABI #Bayes

It was such a pleasure co-organizing AABI this year! We had a great program---with fantastic posters, speakers, and panelists---and talked about topics ranging from approximate inference and smart priors to AI safety and LLMs! 🚀Check out the first-ever AABI proceedings!🚀

I'll be at NeurIPS next week, presenting our work "A Generative Model of Symmetry Transformations." In it, we propose a symmetry-aware generative model that discovers which (approximate) symmetries are present in a dataset, and can be leveraged to improve data efficiency. 🧵⬇️