Dates: 24-26 March 2025
Location: Politecnico di Milano (Aula Rogers)
Welcome to the first edition of the Annual Meeting of EMS-AI activity group on Scientific Machine Learning which brings together scientists from mathematics, computer science, and application areas working on computational and mathematical methods in Scientific Machine Learning.
About
In recent years, the combination of numerical methods and machine learning has gained an ever-increasing interest as a research field within Numerical Mathematics and Scientific Computing. To further foster this development on a European level, the Topical Activity Group Scientific Machine Learning (SciML) of the European Mathematical Society (EMS TAG SciML) has been established.
This is the first edition of the Annual Meeting of EMS-AI activity group on Scientific Machine Learning which aims at bringing together scientists from mathematics, computer science, and application areas working on computational and mathematical methods in Scientific Machine Learning.
This edition will feature 18 invited talks, as well as two industrial sessions, a roundtable discussion, and a poster session.
Round table discussion
The round-table will explore the interplay between machine learning, applied mathematics and scientific computing. The discussion will focus on enhancing understanding of theoretical frameworks, addressing contemporary challenges, and discussing innovative applications in the industrial and scientific sectors.
Professor Wil Schilders, President of the International Council for Industrial and Applied Mathematics (ICIAM) and Full Professor and Chair of Scientific Computing in Industry at the Department of Mathematics and Computer Science at the Technical University of Eindhoven, will chair the round table.
The panel will feature the following distinguished participants:
Safran Tech, Digital Sciences & Technologies, Magny-Les-Hameaux, France
Department of Computer Science, TUM School of Computation, Information, and Technology, Technical University of Munich, Garching, Germany
Max Planck Institute for Dynamics of Complex Technical Systems, Magdeburg, Germany
Laboratory of Intelligent Maintenance and Operations Systems, EPFL, Lausanne, Switzerland
Université de Strasbourg, CNRS, Inria, IRMA, Strasbourg, France
Scientific Computing and Computing Center, University of Kaiserslautern-Landau, Kaiserslautern, Germany
Robert Bosch GmbH, Corporate Sector Research and Advance Engineering, Stuttgart, Germany
INP/ENSEEIHT and Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, Toulouse, France
Department of Earth Science & Engineering, Imperial College London, London, United Kingdom
MOX -Laboratory for Modeling and Scientific Computing, Department of Mathematics, Politecnico di Milano, Milano, Italy
Courant Institute of Mathematical Sciences, New York University, New York, NY, USA
SISSA, International School for Advanced Studies, Trieste, Italy
Dipartimento di Scienze Matematiche "G. L. Lagrange" (DISMA), Politecnico di Torino, Turin, Italy
MOX -Laboratory for Modeling and Scientific Computing, Department of Mathematics, Politecnico di Milano, Milano, Italy
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands
Chief Technology Officer, Moxoff Srl
Dipartimento di Scienze Matematiche "G. L. Lagrange" (DISMA), Politecnico di Torino, Turin, Italy
Department of Mathematics, Humboldt-Universität zu Berlin, Berlin, Germany
Department of Mathematics, ETH-Eidgenössische Technische Hochschule, Zürich, Switzerland
9:15 - 11:15 Tutorial: Learning SciML Models of Dynamical Systems
11:00 - 13:00 Lunch Break
13:00 - 13:30 Opening - Prof. Alberto Guadagnini (Vice Rector for Research, Politecnico di Milano), Prof. Irene M. Sabadini (Head of Department of Mathematics, Politecnico di Milano), Prof. Paola F. Antonietti (Head of MOX Laboratory, Department of Mathematics, Politecnico di Milano) and Prof. Axel Klawonn (Spokesperson for the EMS TAG on SciML)
13:30 - 14:00 Invited Talk - Ben Moseley - Efficient finite-basis physics-informed neural networks
14:00 - 14:30 Invited Talk - Francesco Regazzoni - Integrating physics-based models with scientific machine learning for fast and accurate simulations
14:30 - 15:00 Invited Talk - Alena Kopanicakova - Towards trustworthy use of scientific machine-learning in large scale numerical simulations
15:00 - 15:30 Coffee Break
15:30 - 16:00 Invited Talk - Nicolas Gauger - Solving Distributionally Robust Shape Design Problems by Learning (Discrete) Shape Derivatives
16:00 - 16:30 Invited Talk - Fabien Casenave - Scientific machine learning for industrial design
16:30 - 17:00 Invited Talk - Marius Zeinhofer - Infinite Dimensional Optimization for Scientific Machine Learning
17:00 - 18:00 Business meeting of EMS-TAG on SciML
18:00 - 19:30 Welcome Cocktail & Poster Session
9:30 - 10:00 Invited Talk - Benjamin Peherstorfer - Parametric model reduction of mean-field and stochastic systems via higher-order action matching
10:00 - 10:30 Invited Talk - Emmanuel Franck - Discontinuous Galerkin methods enhanced by neural networks
10:30 - 11:00 Coffee Break
11:00 - 11:30 Invited Talk - Benjamin Sanderse - Scientific Machine Learning for Discovering Closure Models in Multiscale Problems
11:30 - 12:00 Invited Talk - Daniel Walter - Sparsity and sparse optimization in infinite dimensions
12:00 - 14:00 Lunch Break
14:00 - 14:30 Invited Talk - Lihong Feng - All-at-once Parameter-time Sequence Prediction with Deep Learning and Augmented Data
14:30 - 15:00 Invited Talk - Maria Strazzullo - Machine Learning for Turbulence Modeling: Increasing Accuracy in CFD Simulations
15:00 - 15:30 Coffee Break
15:30 - 16:00 Industrial Session - Felix Hildebrand - Scientific Machine Learning in Industry: Some Challenges and Success Stories at Bosch
16:00 - 16:30 Industrial Session - Luigi Simeone - Scientific machine learning solutions for preventive maintenance of home appliances and for aortic abdominal aneurysm risk assessment
16:30 - 17:00 Invited Talk - Federico Pichi - Graph-based machine learning approaches for model order reduction
17:00 - 18:00 Business meeting (internal) of the board EMS-TAG on SciML
9:00 - 9:30 Invited Talk - Sandra Pieraccini - Graph-Instructed Neural Networks: features and applications
9:30 - 10:00 Invited Talk - Felix Dietrich - Scientific Machine Learning with Data-Driven Random Feature Models
10:00 - 10:30 Invited Talk - Olga Fink - Dynami-CAL GraphNet: A Physics-Informed Graph Neural Network Conserving Linear and Angular Momentum for Dynamical Systems
10:30 - 11:00 Coffee Break
11:00 - 12:00 Round Table
12:00 - 12:30 Invited Talk - Stefano Pagani - From Reduced-Order Models to Scientific Machine Learning: Coupling Neural Networks and Differential Models
12:30 - 13:00 Closing
Poster Session Contributions
P.F. Antonietti, S. Pagani, F. Regazzoni, M. Verani (chair), P. Zunino
MOX - Laboratory for Modeling and Scientific Computing, Department of Mathematics, Politecnico di Milano, Milan, Italy
Venue
Building 11, Via Ampère, 2 - 20133 - Milano (MI)
The workshop is located near Piola subway station on Metro Line 2 (MM2 Green Line). Upon arrival at Piola station, please proceed to the left exit. Continue on via Francesco d'Ovidio for ~30 metres, then turn left onto the walkway towards Via Ampère. Once arrived at Via Ampère, make a right turn, which will lead you to the Faculty of Architecture entrance on your left.
For those arriving by train, the closest station is Milano Lambrate, which is a 15-minute walk away. The average travel time from Milan Central Station is 16 minutes by metro (MM2 Green Line), while the journey from Milan Cadorna takes 22 minutes. The Milano Metro map is available at this link.
Poster session Venue: Aula Vetrata - Trifoglio
Building 13, Via Bonardi, 9 - 20133 - Milano (MI)
Accomodation
Some hotels conveniently located near the conference venue are:
This event is supported by:
PRIN 2020