Is this against ICML code?? How should we deal with it... #ICML2022

🤔 To get the best out of your language model, should you be training a GPT-like decoder-only, or an encoder-decoder like T5?

➡️ Uncover the truth at #ICML2022 today: spotlight at 11:45am in room 301-303; poster at 6:30pm in hall E#129.

🔗 icml.cc/virtual/2022/p…

Is it possible that adversarially-trained DNNs are already more robust than the biological neural networks of primate visual cortex? Here is a short thread for our #ICML2022 paper arxiv.org/pdf/2206.11228…. 1/8

📢 Physics + GPs + inverse problems using #ProbabilisticNumerics 📢

At #ICML2022 we show that probabilistic ODE solvers are not just fast, but also useful for solving inverse problems! Joint work with Filip Tronarp and Philipp Hennig. More below 🧵

Excited to introduce our #ICML2022 paper “Probabilistically Robust Learning: Balancing Average- and Worst-case Performance” 🚀

We propose a new, high-probability notion of robustness for machine learning models.

Code: github.com/arobey1/advben…
Paper: arxiv.org/abs/2202.01136

1/n

Train BERT on Smartphones 🤩 Announcing POET 📢 Find out how we train memory-hungry SOTA models on smartphones! #ICML2022 Thu 21 Jul 3:45 pm EDT at Room 327 🧵👇

Paper: arxiv.org/abs/2207.07697
Web: poet.cs.berkeley.edu

Happy to finally share our paper about differentiable Top-K Learning by Sorting that didn’t make it to #CVPR2022 , but was accepted for #ICML2022 ! We show that you can improve classification by actually considering top-1 + runner-ups… 1/6🧵

#ComputerVision #AI #MachineLearning

Excited to present our new #ICML2022 paper on KNN-based OOD detection – a simple and flexible approach without having to make distributional assumptions anymore. 1/n

More insights in the paper: arxiv.org/abs/2204.06507

This Moroccan Arab Muslim first-generation woman just gave her first long talk for her award-winning paper at #ICML2022 ! I dedicate this achievement to all the underrepresented groups that I proudly represent!

So overwhelmed by all the support that I received! Many thanks! 1/2

If you're interested in instrumental variable, invariance and distribution generalization, you may find our paper interesting: proceedings.mlr.press/v162/saengkyon… and if you're at #ICML2022 next week please stop by our poster at Tue 19 Jul 6:30 p.m. — 8:30 p.m.

Excited to share our #ICML2022 paper 'Towards Understanding Sharpness-Aware Minimization'!

Why does m-sharpness matter in m-SAM? Can we explain the benefits of m-SAM on simple models? Which other interesting properties does m-SAM show?

Paper: arxiv.org/abs/2206.06232
🧵1/n

Over-estimation in causality #icml2022

Can Simulation-Based Inference analyses be improved by Bayesian Neural Networks?

In our recent paper in the ML4Astro #ICML2022 workshop, we show that they can, particularly in cases where the simulations fail to model every aspect of the data 🧵

ml4astro.github.io/icml2022/asset…

Are you interested in the generalization capabilities of ImageNet classifiers?

Then attend our workshop! Join us at the ShiftHappens Workshop ICML Conference #ICML2022 this Friday (22 July) 9am - 7:15 pm EST in Ballroom 4!🎉
shift-happens-benchmark.github.io 🧵[1/3]

アンサンブル手法の強み・弱みを要因分析するライブラリ「ensemble-metrics」を公開しました～🙌🙌
良かったら使ってください～。
github.com/hitachi-nlp/en…

#ICML2022 で発表した論文に基づいています。
アンサンブル手法は、複数モデルの予測を混合することで、より高精度な予測を行う手法です。…

「アンサンブル学習における基礎理論の構築」というスライドをアップロードしました～👊👊 #ICML2022 で発表した理論を #JSAI2023 ランチセミナー向けにかみ砕いて説明したものです。

もし良ければ見て下さいー🙂🙂

■内容…

Recommender systems change your preferences and beliefs by exposing you to content. When trained with RL, these systems have the incentive to manipulate your preferences so they are easier to satisfy.

What can we do about this?

Our #ICML2022 📑: arxiv.org/abs/2204.11966

1/n

Interested in principled approaches to handling distribution shift? Went to SCIS and looking for your next fix? Come to the #ICML2022 Workshop on Principles of Distribution Shift ( #PODS ) tomorrow: sites.google.com/view/icml-2022…

We've got an amazing set of speakers and panelists!