Etienne Gauthier
@Gauthier_E_
PhD Student @Inria @ENS_ULM | Multi-agent decision-making, uncertainty quantification
I’ll be presenting our paper at COLT in Lyon this Monday at the Predictions and Uncertainty workshop — come say hi if you're around! 👋 Check out @DHolzmueller's thread below 👇 #COLT2025
For good probability predictions, you should use post-hoc calibration. With @Eugene_Berta, Michael Jordan, and @BachFrancis we argue that early stopping and tuning should account for this! Using the loss after post-hoc calibration often avoids premature stopping. 🧵1/
Me writing the rebuttal to reviewer 2
It is dangerous to be right in matters where established men are wrong.
Had an amazing time at #ICML2025. So many inspiring talks and thoughtful conversations throughout the week! I also gave a talk and got great questions and feedback. ▶️ For anyone interested, here is the recording: icml.cc/virtual/2025/s…
Amazing talk by Aaditya Ramdas on game-theoretic statistics at #ICML2025
🎉 Happy to share that our work "Flowing Datasets with Wasserstein over Wasserstein Gradient Flows" was accepted at #ICML2025 as an oral! This is a joint work with the amazing Christophe Vauthier and @Korba_Anna! Link: openreview.net/forum?id=I1OHP…
Important workshop incoming at #NeurIPS2025 on Algorithmic Collective Action! Looking forward to the conversations.
Announcing the NeurIPS 2025 Workshop on Algorithmic Collective Action: as AI continues to concentrate power, we will meet in San Diego (December 6 or 7) for critical conversations on user coordination, labor, data protection, and community advocacy. #NeurIPS2025 #ACAWorkshop
What if AI isn’t about building solo geniuses, but designing social systems? Michael Jordan advocates blending ML, economics, and uncertainty management to prioritize social welfare over mere prediction. A must-read rethink. arxiv.org/abs/2507.06268…
I will be in Vancouver next week for #ICML2025. Come see my work! 🎤 Talk Thu July 17, 4:00 to 4:15 PM 📍 Oral 6E, Social and Economic Perspectives 🖼️ Poster Thu July 17, 4:30 to 7:00 PM 📍 East Exhibition Hall A-B, E-700 Feel free to reach out :)
🚡 Come check out our poster on understanding LR schedules at ICML. Thursday 11am.
COLT Workshop on Predictions and Uncertainty was a banger! I was lucky to present our paper "Minimum Volume Conformal Sets for Multivariate Regression", alongside my colleague @Eugene_Berta and his awsome work on calibration. Big thanks to the organizers! #ConformalPrediction
Taking a moto taxi against traffic in Delhi gives almost as much adrenaline as when an experiment finally works
Had an amazing time this week at the Game-Theoretic Statistical Inference Workshop in Chennai 🇮🇳 We dove into exciting new developments around e-values and their role in modern statistics. I presented recent work on conformal prediction with e-values 🚀
Happy to have our recent papers on conformal prediction with e-values presented at COLT by my advisor @BachFrancis! Full details here: 📚arxiv.org/abs/2503.13050 📚arxiv.org/abs/2505.13732 #COLT2025
A bit late but happy to share that LLM-SRBench, our new benchmark targeting memorization issue in LLMs for scientific discovery is selected for *Oral* presentation at #ICML2025 ! Great to see the community recognizing the importance of this direction. Checkout the camera-ready…
Scientific discovery with LLMs has so much potential yet is underexplored. Our new benchmark **LLM-SRBench** enable rigorous evaluations of equation discovery with LLMs! 🧠Key takeaway: Even SOTA discovery models with strong LLM backbones still fail to discover mathematical…
Take a break from the heat and check it out!
I’ll be presenting our paper at COLT in Lyon this Monday at the Predictions and Uncertainty workshop — come say hi if you're around! 👋 Check out @DHolzmueller's thread below 👇 #COLT2025
Excited to share that I’m joining NVIDIA as a Principal Research Scientist! We’ll be joining forces on efforts in model post-training, evaluation, agents, and building better AI infrastructure—with a strong emphasis on collaboration with developers and academia. We’re committed…
We uploaded V3 of our draft book "The Elements of Differentiable Programming". Lots of typo fixes, clarity improvements, new figures and a new section on Transformers! arxiv.org/abs/2403.14606