Excited to share my internship project from my time at @DeepMind, looking at sample-efficient imitation learning using entropy-regularized reinforcement learning TL;DR: do behavioral cloning (BC), get inverse reinforcement learning (IRL) for free! [1/6]

👋 Meet Emtiyaz Khan at The Hessian #AICon on July 5! The Team Leader RIKEN Center for Advanced Intelligence Project gives a talk on the topic "How to make machines that adapt quickly" around 1:45 p.m. Check out the agenda & speakers 👉 hessian.ai/aicon-2023/day…. Get your free ticket 👉 hessian.ai/aicon-2023/.

Mathieu Geoffrey Wolfer nominated for top Israeli math prize

At #ICML2023 we will have a workshop on Duality Principles. "Duality is a principle, it gives two different views of the same object" Duality is not a niche topic, it's for everybody. Hope to see you there! dp4ml.github.io/schedule/ Thomas Möllenhoff @ZeldaMariet Mathieu Blondel

The third day of MLRS 2023. Emtiyaz Khan and his team are convincing our participants of the importance of uncertainty in lifelong learning. #MLRS2023 #Bayes #Uncertainty

Inspiring talks by Krikamol (Hiring Postdoc) and Martin Mundt on „(Im)possibility of Collective Intelligence“ and „Self-Expanding Neural Networks“! Thank you for visiting us at RIKEN AIP. 😊

We spent yesterday with Yoshida-team who have another JST CREST・さきがけ・ACT-X CREST grant (just like our The Bayes Duality Project project). Wonderful to visit the Komaba campus of UTokyo, hear about wonderful work on stochastic processes and spatiotemporal models (and have some French food).

We have two open positions in our group in Tokyo (start date is April 2024). Postdoc/research-scientist: riken.jp/en/careers/res… Postdoc or tech-staff (pre-PhD): riken.jp/en/careers/res… Help me spread the word!

The tech-staff position is a really great pre-doc opportunity to jump start your research career in ML. Not only do you get to work with brilliant people at the cutting edge of the field but you get to live/work in the centre of Tokyo. (1/2)

Thomas Möllenhoff and Peter Nickl from our group will also be there presenting their paper on memory perturbation, which generalizes influence function to all sorts of algorithms (arxiv.org/abs/2310.19273), and remove the need to invert matrices. Hope to see you all soon! /end

I'm at NeurIPS for the first time, looking forward to talking about our framework to estimate sensitivity during training at our poster on Wed! Come by if you are interested: Wed 13 Dec 5 p.m. CST — 7 p.m. CST Great Hall & Hall B1+B2 (level 1) #1310 neurips.cc/virtual/2023/p…

Duality dinner at Fogo de Chao, with @ZeldaMariet Thomas Möllenhoff and so many other folks. We will be doing more such meetings in the future (it started at ICML 2023 dp4ml.github.io) Hope more will join in our efforts in the future. Also check out bayesduality.github.io

Excited and humbled that my paper “Conformal Prediction via Regression-as-Classification” was accepted at #ICLR2024! Huge shoutout to my collaborators Emtiyaz Khan, Thomas Möllenhoff, Eugene Ndiaye, Shlok Natarajan! More details coming soon! Paper: etash.me/papers/Bayesia…

Really excited that our work on model merging has been accepted as a poster to ICLR 2024! There have been many discussions recently on model merging on here and many people are questioning why it should work. We try to answer exactly this, as briefly summarized in this thread.

MLSS 2024 is ready!!! See you next Monday!

We don't expect Bayesian methods to do so well at large scale, but we can now get decent improvements with variational learning to GPT-2. I wrote a blog about this (first one in a long time). Check it out! team-approx-bayes.github.io/blog/ivon/ Paper: arxiv.org/abs/2402.17641 A thread below.

✨#ICML2024 Spotlight✨ 🤔 Variational learning is often thought to be impractical. 🔥 Plot twist: it actually works, with improvements over Adam! Meet IVON, a new LLM optimizer that brings the best out of variational learning – 🧵 (1/4) 📰 arxiv.org/abs/2402.17641 #NLProc

The JAX implementation of IVON is now available at github.com/ysngshn/ivon-o… Let us know if you have any issues or success stories to share! #JAX #IVON #deeplearning

Next Thursday, Sept. 12: Seminar on Advances in Probabilistic Machine Learning returns, with Thomas Möllenhoff: Variational Learning is Effective for Large Deep Networks. Register here for the Zoom link: aaltoml.github.io/apml/ cc Arno Solin Computer Science Computer Science @ University of Helsinki RIKEN Center for Advanced Intelligence Project

If you are NeurIPS, feel free to drop by our poster on improving LoRA for LLMs using variational learning. Saturday East Exhibition Hall, 4:40 p.m.–5:30 p.m. (Poster session II). I'm not at NeurIPS this year but please say Hi to Cong Bai who is presenting arxiv.org/abs/2411.04421