PontilGroup Profile Banner
CSML IIT Lab Profile
CSML IIT Lab

@PontilGroup

Followers
28
Following
121
Media
4
Statuses
42

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

Genoa, Italy
Joined November 2024
Don't wanna be here? Send us removal request.
@PontilGroup
CSML IIT Lab
6 months
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
@PontilGroup
CSML IIT Lab
17 days
RT @pie_novelli: New preprint out on arXiv: "Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems"!. Read it….
0
3
0
@PontilGroup
CSML IIT Lab
2 months
RT @OrdonezApraez: Check out our new work on learning ambidexterous bi-manual (and multi-arm) manipulation via morphological symmetry explo….
0
2
0
@PontilGroup
CSML IIT Lab
2 months
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!.
@erfunmirzaei
Erfan Mirzaei
2 months
🚨 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:
Tweet media one
0
2
8
@PontilGroup
CSML IIT Lab
3 months
🚨 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in Scientific ML!.If you’re interested in ML for dynamical systems and/or PDEs, reach out to us directly — the link is outdated, but the position is open!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: #postdoc.
@PontilGroup
CSML IIT Lab
8 months
🚨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: 🌟 #postdocposition #postdoc.
0
1
5
@PontilGroup
CSML IIT Lab
3 months
DeltaProduct is here! Achieve better state tracing through highly parallel execution. Explore more!🚀.
@julien_siems
Julien Siems
4 months
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!
Tweet media one
0
1
3
@PontilGroup
CSML IIT Lab
6 months
[P11] (submitted to The Journal of Chemical Physics). Kooplearn library:. For the longer version of the thread, you can take a look at this blog post:.
0
0
0
@PontilGroup
CSML IIT Lab
6 months
[P7] NeurIPS2024. [P8] NeurIPS2024. [P9] L4DC2024. [P10] (to appear in The International Journal of Robotics Research).
1
0
0
@PontilGroup
CSML IIT Lab
6 months
Publications:.[P1] NeurIPS 2022.. [P2] NeurIPS2023. [P3] ICML2024. [P4] NeurIPS2023. [P5] ICLR 2024. [P6] NeurIPS2024.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
14/ Looking ahead, we’re excited to tackle new challenges:.• Learning from partial observations.• Modeling non-time-homogeneous dynamics.• Expanding applications in neuroscience, genetics, and climate modeling. Stay tuned for groundbreaking updates from our team! 🌍.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
13/ 🙏 Collaborations with the @iitDLSLab group led by Claudio Semini and the @GroupParrinello led by Michele Parrinello enriched our research, resulting in impactful works like [P9, P10] and [P7, P11].
1
0
0
@PontilGroup
CSML IIT Lab
6 months
12/ This journey wouldn’t have been possible without the inspiring collaborations that shaped our work. 🌟 Special thanks to Karim Lounici from École Polytechnique, whose insights were a major driving force behind many projects.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
11/ One of our most exciting results:.[P8] NeurIPS 2024 proposed Neural Conditional Probability (NCP) to efficiently learn conditional distributions. It simplifies uncertainty quantification and guarantees accuracy for nonlinear, high-dimensional data.
Tweet media one
1
0
0
@PontilGroup
CSML IIT Lab
6 months
10/ [P7] NeurIPS 2024 developed methods to discover slow dynamical modes in systems like molecular simulations. This is transformative for studying rare events and costly data acquisition scenarios in atomistic systems.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
9/ Addressing continuous dynamics:.[P6] NeurIPS 2024 introduced a physics-informed framework for learning Infinitesimal Generators (IG) of stochastic systems, ensuring robust spectral estimation.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
8/ 🌟 Representation learning takes center stage in:.[P5] ICLR 2024.We combined neural networks with operator theory via Deep Projection Networks (DPNets). This approach enhances robustness, scalability, and interpretability for dynamical systems.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
7/ 📈 Scaling up:.[P4] NeurIPS 2023 introduced a Nyström sketching-based method to reduce computational costs from cubic to almost linear without sacrificing accuracy. Validated on massive datasets like molecular dynamics, see figure.
Tweet media one
1
0
0
@PontilGroup
CSML IIT Lab
6 months
6/ [P3] ICML 2024 addressed a critical issue in TO-based modeling: reliable long-term predictions. Our Deflate-Learn-Inflate (DLI) paradigm ensures uniform error bounds, even for infinite time horizons. This method stabilized predictions in real-world tasks; see the figure.
Tweet media one
1
0
0
@PontilGroup
CSML IIT Lab
6 months
5/ [P2] NeurIPS 2023 advanced TOs with theoretical guarantees for spectral decomposition—previously lacking finite sample guarantees. We developed sharp learning rates, enabling accurate, reliable models for long-term system behavior.
1
0
0
@PontilGroup
CSML IIT Lab
6 months
4/ 🔑 The journey began with:.[P1] NeurIPS 2022.We introduced the first ML formulation for learning TO, which led to the development of the open-source Kooplearn library. This step laid the groundwork for exploring the theoretical limits of operator learning from finite data.
Tweet media one
1
0
0
@PontilGroup
CSML IIT Lab
6 months
3/TOs describe system evolution over finite time intervals, while IGs capture instantaneous rates of change. Their spectral decomposition is key for identifying dominant modes and understanding long-term behavior in complex or stochastic systems.
1
0
0