Connectionists: Post-doc in Scientific Machine Learning at The Italian Institute of Technology

[massimiliano.pontil at gmail.com]

We are seeking a talented and motivated Postdoc to join the Computational
Statistics and Machine Learning
<https://www.iit.it/it/web/computational-statistics-and-machine-learning>
Research
Units at IIT, led by Prof. Massimiliano Pontil. The successful candidate
will be engaged in designing novel learning algorithms for numerical
simulations of physical systems, with a focus on machine learning for
dynamical systems. CSML’s core focus is on ML theory and algorithms, while
significant multidisciplinary interactions with other IIT groups apply our
research outputs in areas ranging from Atomistic Simulations to
Neuroscience and Robotics. We have also recently started international
collaboration on Climate Modelling. The group hosts applied mathematicians,
computer scientists, physicists, and computer engineers, working together
on theory, algorithms and applications. ML techniques, coupled with
numerical simulations of physical systems have the potential to
revolutionize the way in which science is conducted. Meeting this challenge
requires a multi-disciplinary approach in which experts from different
disciplines work together. Candidates with a strong background in a least
one of the following areas will be given priority in hiring: 1) ML for
dynamical systems and partial differential equations; 2) Computational
tools for numerical simulations, and a working knowledge of ML tools; 3)
Numerical optimization and its application to machine learning and deep
learning.

For recent relevant publications from our lab, please see:

   -

   V. Kostic, P. Novelli, A. Maurer, C. Ciliberto, L. Rosasco, M.
Pontil. Learning
   dynamical systems via Koopman operator regression in reproducing kernel
   hilbert spaces
   <https://proceedings.neurips.cc/paper_files/paper/2022/hash/196c4e02b7464c554f0f5646af5d502e-Abstract-Conference.html>.
   NeurIPS 2022.
   -

   V. Kostic, P. Novelli, R. Grazzi, K. Lounici, M. Pontil. Learning
   invariant representations of time-homogeneous stochastic dynamical systems
   <https://arxiv.org/abs/2307.09912>. ICLR 2024.
   -

   V. Kostic, K. Lounici, H. Halconruy, T. Devergne, M. Pontil. Learning
   the infinitesimal generator of stochastic diffusion processes
   <https://arxiv.org/abs/2405.12940>. NeurIPS 2024
   -

   T. Devergne, V. Kostic, M. Parrinello, M. Pontil. From biased to
   unbiased dynamics: an infinitesimal generator approach.
   <https://arxiv.org/abs/2406.09028> NeurIPS, 2024.
   -

   P Novelli, L Bonati, M Pontil, M Parrinello. Characterizing metastable
   states with the help of machine learning
   <https://scholar.google.com/citations?view_op=view_citation&hl=en&user=bXlwJucAAAAJ&citation_for_view=bXlwJucAAAAJ:u-x6o8ySG0sC>
   . Journal of Chemical Theory and Computation 18 (9), 5195-5202, 2022.
   -

   J Falk, L Bonati, P Novelli, M Parrinello, M Pontil. Transfer learning
   for atomistic simulations using GNNs and kernel mean embeddings
   <https://scholar.google.com/citations?view_op=view_citation&hl=en&user=bXlwJucAAAAJ&citation_for_view=bXlwJucAAAAJ:YsMSGLbcyi4C>
   . NeurIPS, 2023.
   -

   R Grazzi, M Pontil, S Salzo. Bilevel Optimization with a Lower-level
   Contraction: Optimal Sample Complexity without Warm-Start
   <https://scholar.google.com/citations?view_op=view_citation&hl=en&user=9Tlyx1IAAAAJ&citation_for_view=9Tlyx1IAAAAJ:YsMSGLbcyi4C>.
   Journal of Machine Learning Research 24 (167), 1-37

Please submit your application using the online form and CV, a short
research statement (max 2 pages) and names of two referees.

Application link:
<https://iit.taleo.net/careersection/ex/jobdetail.ftl?lang=en&job=2300004C>
https://iit.taleo.net/careersection/ex/jobdetail.ftl?lang=en&job=2400006W
Deadline: November 10, 2024.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20241007/adca56f8/attachment.html>