Pantelis R. Vlachas

Head of Machine Learning, AI2C Technologies & Associate Researcher, ETH Zurich

vlachas_pic.jpeg

Hi!

I’m Pantelis, currently leading the Machine Learning Research team at AI2C Technologies, a spin-off from ETH working on novel machine learning solutions for fintech. In parallel, I am affiliated with ETH Zurich, with the group of Prof. Eleni Chatzi, where I am exploring adaptive surrogate models of dynamical systems with online and real-time learning capabilities.

I completed my Ph.D. under the supervision of Prof. Petros Koumoutsakos in the CSE Lab in Zurich. There I worked on novel efficient methods for learning effective dynamics of complex systems. We demonstrated the effectiveness of the developed methods in a wide range of applications from systems that exhibit spatiotemporal chaotic behavior and turbulent flows to small molecules. During my Ph.D. I also visited the John A. Paulson School Of Engineering And Applied Sciences in Harvard as an Associate Researcher.

Feel free to reach out!

news

Aug 25, 2023 My collegues Pascal Weber and Michalis Chatzimanolakis successfully defended their PhDs! Their work on Reinforcement learning for fish schooling behavior and adaptive mesh refinement has been remarkable (and also super cool). Check it out!
Aug 1, 2023 Our paper on Adaptive learning of effective dynamics for online modeling of complex systems has been published in the journal of Computer Methods in Applied Mechanics and Engineering (CMAME)! This is joint work with Ivica Kičić, Michalis Chatzimanolakis, Prof. Petros Koumoutsakos, Prof. Leonidas Guibas, and George Arampatzis.
Sep 26, 2022 I gave a talk at the Third Symposium on Machine Learning and Dynamical Systems in Toronto. Very interesting conference with lots of remarkable talks organized by Boumediene Hamzi. Link to the talk here.
Apr 8, 2022 The paper Multiscale simulations of complex systems by learning their effective dynamics was published in Nature Machine Intelligence!
Sep 21, 2020 I gave a talk at the Second Symposium on Machine Learning and Dynamical Systems in Toronto organized by Boumediene Hamzi. Link to the talk here. All talks of the data-driven modeling session can be found here.