Aurelien Lucchi

Excited to share our latest work on bridging theory & practice in optimization 🚀 We study stochastic conditional methods with momentum and provide practical strategies for choosing batch size and Frank–Wolfe stepsizes when token budget increases Paper: arxiv.org/abs/2603.21191

🚨 New Benchmark Alert!! 🚨 Navigate Wikipedia hyperlinks step-by-step. No map. Just planning and world knowledge! We evaluated 20+ models on 3 difficulty levels: Gemini-3: 95% → 66% → 23% GPT-5: 92.5% → 60% → 15% Opus 4.5: 91.5% → 56% → 18% We discover a Planning Gap!🧵

@ilijabogunovic 100%. I don't think this solves the problem and it introduces more randomness in the process as we will have new ACs who are unfamiliar with the papers and outdated reviews/scores.

The ICLR measure to prevent collusion is absolutely wrong. How did they decide upon 1., 2. and 3.? The ACs can't do their reviewers' jobs! #ICLR2026

Want to do a PhD on RL for LLMs? 🇨🇭🤖🎓 One week left to apply!

And Switzerland offers a remarkable diversity of landscapes, from alpine peaks to tranquil lakes.

The conditions to create a group in Switzerland are among the best in the world: significant fundings for PhD students, high acceptance rate from the funding agency SNF, access to European funding opportunities, lots of amazing PhD candidates, great research partners, etc.

The University of Basel has an opening for a Professorship in Deep Learning. We are growing, join us! jobs.unibas.ch/offene-stellen…

@ilijabogunovic and I are looking for two PhD candidates in the field of reasoning in machine learning. Apply here: jobs.unibas.ch/offene-stellen…

Post-doc position in the field of Optimization and Deep Learning Theory jobs.unibas.ch/offene-stellen… PhD position in the field of Optimization and Deep Learning Theory jobs.unibas.ch/offene-stellen… PhD position in the field of Reasoning in Machine Learning jobs.unibas.ch/offene-stellen…

Our research group in the department of Mathematics and CS at the University of Basel (Switzerland) is looking for several PhD candidates and one post-doc who have a theoretical background in optimization and machine learning or practical experience in reasoning. RT please.

We have a non-vanishing term in the convergence rate, and interestingly this term decreases when we increase the number of parameters (confirmed experimentally and in line with many other prior works in the field):

We also characterize the convergence of SGD (and other optimizers):

Loss Landscape Characterization of Neural Networks without Over-Parametrization to appear at @NeurIPSConf 2024. We propose a novel class of functions that characterize the loss landscape of deep models without requiring over-parametrization. arxiv.org/pdf/2410.12455

@jmtomczak @aramezanik @ulrichpaquet @DaniCMBelg Thank you for taking this seriously, I just wrote an official email.

@AurelienLucchi @aramezanik @ulrichpaquet @DaniCMBelg Please write an official email, then we can look into your case.

#neurips2024 An adversarial AC rejected our paper with avg score of 6.3 with ALL Reviewers accepted the paper because "the reviewers were not responding on a clear paper during discussion" WTH is going on? @jmtomczak @ulrichpaquet @DaniCMBelg Any accountability for such an AC?

Switzerland offers very attractive conditions to do research: good salaries, excellent research institutions, access to international networks, high quality of life, etc. Many of our graduates end up with great jobs, both in academia and industry. Please retweet too, thank you!

See details here: jobs.unibas.ch/offene-stellen…

My group has multiple openings both for PhD and Post-doc positions to work in the area of optimization for ML, and deep learning theory. We are looking for people with a strong theoretical background (degree in math, theoretical physics or CS with strong theory emphasis).