Computational Statistics and Machine Learning Lab @IITtalk | PI: @MPontil | Statistical learning theory, ML for dynamical systems, ML for science, optimization.
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! 🧵👇
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:
🔗 https://t.co/nkukNnkw2j
🚨 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).
https://t.co/nkukNnkw2j
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!
📢 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
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.
📢 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
👉 https://t.co/h1Io7BykqX
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.
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!
🚨 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: https://t.co/XNBVao1Nym
🚨 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: https://t.co/7RryN0IpM1
#postdoc
🚨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: https://t.co/7RryN0IXBz 🌟 #postdocposition#postdoc
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!
[P11] (submitted to The Journal of Chemical Physics)
https://t.co/FmbNjxdwR8
Kooplearn library:
https://t.co/lcMLgdReYy
For the longer version of the thread, you can take a look at this blog post:
https://t.co/XnNtoYKPPc
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! 🧵👇
[P7] NeurIPS2024
https://t.co/TS1Ti4lsf7
[P8] NeurIPS2024
https://t.co/koweWv4skB
[P9] L4DC2024
https://t.co/mBNTQvq3le
[P10] (to appear in The International Journal of Robotics Research)
https://t.co/0X7BNP6cHw