@PontilGroup

Computational Statistics and Machine Learning Lab @IITtalk | PI: @MPontil | Statistical learning theory, ML for dynamical systems, ML for science, optimization.

 Genoa, Italy
csml.iit.it/
Joined November 2024
  • Tweets57
  • Following32
  • Followers32
5Media
1/ 🚀 Over the past two years, our team, CSML, at IIT, has made significant strides in the data-driven modeling of dynamical systems. Curious about how we use advanced operator-based techniques to tackle real-world challenges? Let’s dive in! 🧵👇
1
2
2
406
Looking for your next step in machine learning research? Join our team! We have an open #postdoc position in #MachineLearning & dynamical systems. Set in a vibrant research environment (with great colleagues, food, and sea views included). Details and application link below
ELLIS@ELLISforEuropeOct 16
🏹 Job alert: Postdoctoral researcher in Machine Learning and Dynamical Systems at Italian Institute of Technology (IIT) 📍 Genoa 🇮🇹 ⏰ 31 October 🔗 bit.ly/4B4pfXI

Postdoctoral researcher in Machine Learning and Dynamical Systems

Contract and commitment: collaboration contract, for up to three yearsLocation: CHT Erzelli, Genoa, Italy Step into a world of endless possibilities, together let’s leave something for the future! At...

app.ncoreplat.com
1
2
3
121
📢 We’re hiring! 🧠 Excited about ML foundations & dynamical systems? We have an open Postdoc position in Massimiliano Pontil's CSML unit at @IITalk (Genoa, Italy 🇮🇹) on the ERC "LEO" project! ⏳ Up to 3 years 📅 Deadline: October 31, 2026 Details: 👇 app.ncoreplat.com/jobpositio…

Postdoctoral researcher in Machine Learning and Dynamical Systems

Contract and commitment: collaboration contract, for up to three yearsLocation: CHT Erzelli, Genoa, Italy Step into a world of endless possibilities, together let’s leave something for the future! At...

app.ncoreplat.com
3
6
309
Representations for the Physical Sciences Workshop @ NeurIPS 2026🇫🇷 We’re bringing together researchers working on AI for science, representation learning, and physical systems, with a particular focus on self-supervision, transfer learning, adaptive sampling, and tokenization.
1
1
1
3
400
We invite 4-page, non-archival short papers, with accepted work presented as posters and selected contributions invited for talks. 📅 Submission deadline: August 29 (AoE) 📍 Paris — NeurIPS 2026, December 12 or 13 🌐 Website: representations-physical-sci…
27
ICML 2026 is underway in Seoul, and I'm delighted that our group has four papers on the program this week: 📍 Tuesday, July 7 · Hall A · Poster #4413 Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression icml.cc/virtual/2026/poster/…
1
6
175
more replies
📍 Wednesday, July 8 · 5:00–6:45 PM KST · Hall A · Poster #4401 Representation Learning for Equivariant Inference with Guarantees icml.cc/virtual/2026/poster/…
1
2
25
📍 Thursday, July 9 · 5:00–6:45 PM KST · Hall A · Poster #4517 Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime icml.cc/virtual/2026/poster/… If you're attending ICML, we'd be delighted to see you at the posters and discuss our work.
1
2
576
Almost 5 years in the making... "Hyperparameter Optimization in Machine Learning" is finally out! 📘🚀 From basic tuning to Bayesian optimization and meta-learning, we show how these techniques tie together in one self-contained guide. Check it out: 🔗 arxiv.org/abs/2410.22854
3
7
183
🚨 OpenReview might have leaked names, but it won't leak the best hyperparameters, unfortunately! 😅 Tired of the drama? Solve your HPO problems before the ICML deadline with this new book by our own Luca Franceschi & Massimiliano Pontil (& colleagues). arxiv.org/abs/2410.22854

Hyperparameter Optimization in Machine Learning

Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the choice of their...

arxiv.org
1
1
4
289
📢 Upcoming Talk at Our Lab We’re excited to host Arthur Bizzi from EPFL for a research talk next week! Title: Towards Neural Kolmogorov Equations: Parallelizable SDE Learning with Neural PDEs 🗓 Date: November 19 ⏰ Time: 16:00 CET 📍 Galileo Sala, CHT @IITalk
1
1
3
127
more replies
In this talk, Arthur Bizzi will introduce Neural Kolmogorov Equations, a deterministic and parallelizable framework for learning continuous-time stochastic processes using Forward and Backward Kolmogorov Equations.
1
2
27
He will also present an entropy-respecting forward–backward learning scheme that mitigates the inherent ill-posedness of stochastic learning problems. Join us for what promises to be a very insightful session!
2
18
📢 Now it’s out on arXiv! If you’re interested in theoretical guarantees for learning with dependent Hilbert-space data, check out our full paper: 📝 An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications 👉 arxiv.org/abs/2507.07826

An Empirical Bernstein Inequality for Dependent Data in Hilbert...

Learning from non-independent and non-identically distributed data poses a persistent challenge in statistical learning. In this study, we introduce data-dependent Bernstein inequalities tailored...

arxiv.org
Erfan Mirzaei@erfunmirzaei2 May 2025
🚨 Poster at #AISTATS2025 tomorrow! 📍Poster Session 1 #125 We present a new empirical Bernstein inequality for Hilbert space-valued random processes—relevant for dependent, even non-stationary data. w/ Andreas Maurer, @vkostic30 & @MPontil 📄 Paper: openreview.net/forum?id=a0EX…
3
2
12
998
New preprint out on arXiv: "Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems"! Read it here: pietronvll.github.io/encoder…
1
3
4
435
Check out our new work on learning ambidexterous bi-manual (and multi-arm) manipulation via morphological symmetry exploitation with Equivariant NNs. Kudos to @softraeh for leading this work.
Zechu Li@softraeh9 May 2025
Unlike humans who favor a dominant hand for fine dexterous skills, robots should execute ambidextrous manipulation with equal proficiency. Introducing SYMDEX, our algorithm for Ambidextrous Bimanual Manipulation leveraging robot’s inherent bilateral symmetry as an inductive bias.
1
2
7
604
Excited to share our group’s latest work at #AISTATS2025! 🎓 Tackling concentration in dependent data settings with empirical Bernstein bounds for Hilbert space-valued processes. 📍Catch the poster tomorrow! 🔁 See original tweet for details!
Erfan Mirzaei@erfunmirzaei2 May 2025
🚨 Poster at #AISTATS2025 tomorrow! 📍Poster Session 1 #125 We present a new empirical Bernstein inequality for Hilbert space-valued random processes—relevant for dependent, even non-stationary data. w/ Andreas Maurer, @vkostic30 & @MPontil 📄 Paper: openreview.net/forum?id=a0EX…
2
8
247
🚨 We’re still hiring for this exciting Postdoc in Scientific ML! If you’re interested in ML for dynamical systems and/or PDEs, reach out to us directly — the link is outdated, but the position is open! 📩Contact us! 🔁RTs appreciated More info: ellis.eu/jobs/post-doc-in-sc… #postdoc
CSML IIT Lab@PontilGroup20 Nov 2024
🚨Postdoc Opportunity in Scientific Machine Learning 🚨 Join us in designing cutting-edge learning algorithms for simulating physical systems! Focus on ML for dynamical systems. @ELLISforEurope @IITalk Details: ellis.eu/jobs/post-doc-in-sc… 🌟 #postdocposition #postdoc
1
1
5
459
DeltaProduct is here! Achieve better state tracing through highly parallel execution. Explore more!🚀
Julien Siems@julien_siems28 Mar 2025
1/9 There is a fundamental tradeoff between parallelizability and expressivity of Large Language Models. We propose a new linear RNN architecture, DeltaProduct, that can effectively navigate this tradeoff. Here's how!
1
3
150
Load more