Peter Nickl

PhD @ Pouget Lab @NeuroGeneva @pouget_alex | previously RA @ Adaptive Bayesian Intelligence Team @RIKEN_AIP_EN @RIKEN_EN | MSc @TUDarmstadt @ias_tudarmstadt

[Thomas Möllenhoff @tmoellenhoff]

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 https://t.co/mqSzDerK6b

[Finnish Center for AI 🦣 @[email protected] @FCAI_fi]

Next Thursday, Sept. 12: Seminar on Advances in Probabilistic Machine Learning returns, with @tmoellenhoff: Variational Learning is Effective for Large Deep Networks.
Register here for the Zoom link: https://t.co/hJq0TrtswY
cc @arnosolin @CSAalto @UnivHelsinkiCS @RIKEN_AIP_EN

[Yuesong Shen @ysngshn]

The JAX implementation of IVON is now available at https://t.co/LcB5leVI6o Let us know if you have any issues or success stories to share! #JAX #IVON #deeplearning

[UKP Lab @UKPLab]

✨#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)

📰 https://t.co/GLCqCezNJJ

#NLProc

[Emtiyaz Khan @EmtiyazKhan]

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!
https://t.co/c7ftgBol2x

Paper: https://t.co/GUFi1br9av

A thread below.

[myamada0 @myamada0]

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

[Etash Guha @etash_guha]

Excited and humbled that my paper “Conformal Prediction via Regression-as-Classification” was accepted at #ICLR2024! Huge shoutout to my collaborators @EmtiyazKhan, @tmoellenhoff, @eugene_ndiaye, @Shlok_Natarajan! More details coming soon!

Paper: https://t.co/iC9i5V4xqa

[Nico Daheim @ndaheim_]

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.

[Emtiyaz Khan @EmtiyazKhan]

Duality dinner at Fogo de Chao, with @ZeldaMariet @tmoellenhoff and so many other folks.

We will be doing more such meetings in the future (it started at ICML 2023 https://t.co/SVv3XYsgLR)

Hope more will join in our efforts in the future. Also check out https://t.co/SEL4hperSk

[Peter Nickl @PeterNickl_]

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
https://t.co/5ht6l64SlL

[Thomas Möllenhoff @tmoellenhoff]

First time at NeurIPS since 2019. I'm presenting our work on deriving influence measures from a Bayesian viewpoint (with @EmtiyazKhan @PeterNickl_ @dtailor17 @L_u_X_u). Suggests cheap ways of computing influence also during training. Please say hi:)
https://t.co/IbUXrWsbne

[Emtiyaz Khan @EmtiyazKhan]

@tmoellenhoff and @PeterNickl_ from our group will also be there presenting their paper on memory perturbation, which generalizes influence function to all sorts of algorithms (https://t.co/rqXsAa6EoF), and remove the need to invert matrices.

Hope to see you all soon!

/end

[Dharmesh Tailor @dtailor17]

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)

[Emtiyaz Khan @EmtiyazKhan]

We have two open positions in our group in Tokyo (start date is April 2024).

Postdoc/research-scientist: https://t.co/BSoTLTmNyJ
Postdoc or tech-staff (pre-PhD): https://t.co/4oUoVHq4U7

Help me spread the word!

[Emtiyaz Khan @EmtiyazKhan]

We spent yesterday with Yoshida-team who have another @JST_Kisokenkyu CREST grant (just like our @BayesDuality project). Wonderful to visit the Komaba campus of UTokyo, hear about wonderful work on stochastic processes and spatiotemporal models (and have some French food).

[Thomas Möllenhoff @tmoellenhoff]

Inspiring talks by @krikamol and @mundt_martin on „(Im)possibility of Collective Intelligence“ and „Self-Expanding Neural Networks“! Thank you for visiting us at RIKEN AIP. 😊

[Krikamol (Hiring Postdoc) @krikamol]

The third day of MLRS 2023. @EmtiyazKhan and his team are convincing our participants of the importance of uncertainty in lifelong learning.

#MLRS2023 #Bayes #Uncertainty

[Emtiyaz Khan @EmtiyazKhan]

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!
https://t.co/sIIidet1mc
@tmoellenhoff @ZeldaMariet @mblondel_ml

[Aryeh Kontorovich @aryehazan]

@miniapeur @geowolfer nominated for top Israeli math prize

[hessian.AI @Hessian_AI]

👋 Meet @EmtiyazKhan at The Hessian #AICon on July 5! The Team Leader @RIKEN_AIP_EN gives a talk on the topic "How to make machines that adapt quickly" around 1:45 p.m. Check out the agenda & speakers 👉 https://t.co/2wmDFeJyVY.
Get your free ticket 👉 https://t.co/I2roxCUoEv.

[Joe Watson @JoeMWatson]

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]