<div dir="ltr"><p dir="ltr" style="text-align:left;line-height:1.656;margin-top:0pt;margin-bottom:0pt;padding:11pt 0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(51,51,51);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">We are seeking a talented and motivated Postdoc to join the </span><a href="https://www.iit.it/it/web/computational-statistics-and-machine-learning" style="text-decoration-line:none" target="_blank"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,255);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;text-decoration-line:underline;vertical-align:baseline">Computational Statistics and Machine Learning</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(51,51,51);font-style:italic;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(51,51,51);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Research Units at IIT, led by Prof. Massimiliano Pontil. </span><span style="font-size:10.5pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">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</span><span style="font-size:10pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> 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.</span></p><p dir="ltr" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10.5pt;font-family:Arial,sans-serif;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">For recent relevant publications from our lab, please see:</span></p><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:11pt;margin-bottom:0pt"><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">V. Kostic, P. Novelli, A. Maurer, C. Ciliberto, L. Rosasco, M. Pontil.</span><a href="https://proceedings.neurips.cc/paper_files/paper/2022/hash/196c4e02b7464c554f0f5646af5d502e-Abstract-Conference.html" style="text-decoration-line:none" target="_blank"><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><font color="#0000ff">Learning dynamical systems via Koopman operator regression in reproducing kernel hilbert spaces</font></span></a><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">. NeurIPS 2022.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">V. Kostic, P. Novelli, R. Grazzi, K. Lounici, M. Pontil.</span><a href="https://arxiv.org/abs/2307.09912" style="text-decoration-line:none" target="_blank"><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><font color="#0000ff">Learning invariant representations of time-homogeneous stochastic dynamical systems</font></span></a><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><font color="#0000ff">. </font></span><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">ICLR 2024.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">V. Kostic, K. Lounici, H. Halconruy, T. Devergne, M. Pontil. </span><font color="#0000ff"><a href="https://arxiv.org/abs/2405.12940" style="text-decoration-line:none" target="_blank"><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Learning the infinitesimal generator of stochastic diffusion processes</span></a>.</font><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> NeurIPS 2024</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">T. Devergne, V. Kostic, M. Parrinello, M. Pontil.</span><font color="#0000ff"><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span><a href="https://arxiv.org/abs/2406.09028" style="text-decoration-line:none" target="_blank"><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">From biased to unbiased dynamics: an infinitesimal generator approach.</span></a></font><span style="color:rgb(26,26,26);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> NeurIPS, 2024.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(0,0,0);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">P Novelli, L Bonati, M Pontil, M Parrinello. </span><a href="https://scholar.google.com/citations?view_op=view_citation&hl=en&user=bXlwJucAAAAJ&citation_for_view=bXlwJucAAAAJ:u-x6o8ySG0sC" style="text-decoration-line:none" target="_blank"><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><font color="#0000ff">Characterizing metastable states with the help of machine learning</font></span></a>.<span style="color:rgb(0,0,0);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> Journal of Chemical Theory and Computation 18 (9), 5195-5202, 2022.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(0,0,0);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">J Falk, L Bonati, P Novelli, M Parrinello, M Pontil. </span><font color="#0000ff"><a href="https://scholar.google.com/citations?view_op=view_citation&hl=en&user=bXlwJucAAAAJ&citation_for_view=bXlwJucAAAAJ:YsMSGLbcyi4C" style="text-decoration-line:none" target="_blank"><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Transfer learning for atomistic simulations using GNNs and kernel mean embeddings</span></a><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">.</span><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span></font><span style="color:rgb(0,0,0);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">NeurIPS, 2023.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:10.5pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><p dir="ltr" role="presentation" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:11pt"><span style="color:rgb(0,0,0);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">R Grazzi, M Pontil, S Salzo. </span><font color="#0000ff"><a href="https://scholar.google.com/citations?view_op=view_citation&hl=en&user=9Tlyx1IAAAAJ&citation_for_view=9Tlyx1IAAAAJ:YsMSGLbcyi4C" style="text-decoration-line:none" target="_blank"><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><font color="#0000ff">Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start</font></span></a><span style="font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">. </span></font><span style="color:rgb(0,0,0);font-size:10.5pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Journal of Machine Learning Research 24 (167), 1-37</span></p></li></ul><p dir="ltr" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10.5pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Please submit your application using the online form and </span><span style="font-size:10.5pt;font-family:Arial,sans-serif;color:rgb(51,51,51);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">CV, a short research statement (max 2 pages) and names of two referees.</span></p><p dir="ltr" style="text-align:left;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Application link:</span><a href="https://iit.taleo.net/careersection/ex/jobdetail.ftl?lang=en&job=2300004C" style="text-decoration-line:none" target="_blank"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(17,85,204);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;text-decoration-line:underline;vertical-align:baseline"><a href="https://iit.taleo.net/careersection/ex/jobdetail.ftl?lang=en&job=2400006W" target="_blank">https://iit.taleo.net/careersection/ex/jobdetail.ftl?lang=en&job=2400006W</a></span></p><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Deadline: </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">November 10, 2024.</span><br></div>