POST-DOC IN SCIENTIFIC MACHINE LEARNING

• (2400006W)
  Commitment & contract: at least 2 Years
  Location: IIT Erzelli, Genova
  WHO WE ARE: At IIT we work enthusiastically to develop human-centered Science and Technology to tackle some of the most pressing societal challenges of our times and transfer these technologies to the production system and society. Our Genoa headquarter is strictly inter-connected with our 11 centers around Italy and two outer-stations based in the US for a truly interdisciplinary experience.
  YOUR TEAM: The position is within the Computational Statistics and Machine Learning (CSML) research unit at IIT. 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 has a strong focus on ML theory and algorithms, but also significant multidisciplinary interactions with other IIT groups 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 both theory, algorithms and applications. Machine learning 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.

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. NeurIPS 2022.
• V. Kostic, P. Novelli, R. Grazzi, K. Lounici, M. Pontil. Learning invariant representations of time-homogeneous stochastic dynamical systems. ICLR 2024.
• V. Kostic, K. Lounici, H. Halconruy, T. Devergne, M. Pontil. Learning the infinitesimal generator of stochastic diffusion processes, Submitted 2024
• T. Devergne, V. Kostic, M. Parrinello, M. Pontil. From biassed to unbiased dynamics: an infinitesimal generator approach. Submitted, 2024.
• P Novelli, L Bonati, M Pontil, M Parrinello. Characterizing metastable states with the help of machine learning 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. NeurIPS, 2023.
• R Grazzi, M Pontil, S Salzo. Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start. Journal of Machine Learning Research 24 (167), 1-37

Within the team your main responsibilities will be:

• to investigate open research problems in machine learning and computational physics,
• to write research papers and when appropriate, open source software to fully reproduce the results presented in the papers,
• possibly, to be involved in coaching PhD students and interns.

• to investigate open research problems in machine learning and computational physics,
• to write research papers and when appropriate, open source software to fully reproduce the results presented in the papers,
• possibly, to be involved in coaching PhD students and interns