Machine learning methods have had great success in learning complex representations that enable them to make predictions about unobserved data. Physical sciences span problems and challenges at all scales in the universe: from finding exoplanets in trillions of sky pixels, to finding machine learning inspired solutions to the quantum many-body problem, to detecting anomalies in event streams from the Large Hadron Collider. Tackling a number of associated data-intensive tasks including, but not limited to, segmentation, 3D computer vision, sequence modeling, causal reasoning, and efficient probabilistic inference are critical for furthering scientific discovery. In addition to using machine learning models for scientific discovery, the ability to interpret what a model has learned is receiving an increasing amount of attention.
In this targeted workshop, we would like to bring together computer scientists, mathematicians and physical scientists who are interested in applying machine learning to various outstanding physical problems, in particular in inverse problems and approximating physical processes; understanding what the learned model really represents; and connecting tools and insights from physical sciences to the study of machine learning models. In particular, the workshop invites researchers to contribute papers that demonstrate cutting-edge progress in the application of machine learning techniques to real-world problems in physical sciences, and using physical insights to understand what the learned model means.
By bringing together machine learning researchers and physical scientists who apply machine learning, we expect to strengthen the interdisciplinary dialogue, introduce exciting new open problems to the broader community, and stimulate production of new approaches to solving open problems in sciences. Invited talks from leading individuals in both communities will cover the state-of-the-art techniques and set the stage for this workshop.
Opening Remarks | |
Atilim Gunes Baydin, Juan Carrasquilla, Shirley Ho, Karthik Kashinath, Michela Paganini, Savannah Thais, Anima Anandkumar, Kyle Cranmer, Roger Melko, Mr. Prabhat, Frank Wood |
Bernhard Schölkopf (Invited Talk 1) | |
Bernhard Schölkopf |
Towards physics-informed deep learning for turbulent flow prediction (Contributed talk 1) | |
Rose Yu |
JAX, M.D.: End-to-End Differentiable, Hardware Accelerated, Molecular Dynamics in Pure Python (Contributed Talk 2) | |
Sam Schoenholz |
Morning Coffee Break & Poster Session (Coffee Break) | |
Eric Metodiev, Keming Zhang, Markus Stoye, Michael Churchill, Soumalya Sarkar, Miles Cranmer, Johann Brehmer, Danilo Jimenez Rezende, Peter Harrington, Akshat Nigam, Nils Thuerey, Lukasz Maziarka, Alvaro Sanchez Gonzalez, Atakan Okan, James Ritchie, N. Benjamin Erichson, Harvey Cheng, Peihong Jiang, Seong Ho Pahng, Samson Koelle, Sami Khairy, Adrian Pol, Rushil Anirudh, Jannis Born, Benjamin Sanchez-Lengeling, Brian Timar, Rhys Goodall, Tamás Kriváchy, Lu Lu, Thomas Adler, Nat Trask, Noëlie Cherrier, Tomo Konno, Muhammad Kasim, Tobias Golling, Zaccary Alperstein, Andrei Ustyuzhanin, James Stokes, Anna Golubeva, Ian Char, Ksenia Korovina, Youngwoo Cho, Chanchal Chatterjee, Tom Westerhout, Gorka Muñoz-Gil, Juan Zamudio-Fernandez, Jennifer Wei, Brian Lee, Johannes Kofler, Bruce Power, Nikita Kazeev, Andrey Ustyuzhanin, Artem Maevskiy, Pascal Friederich, Arash Tavakoli, Willie Neiswanger, Bohdan Kulchytskyy, sindhu hari, Paul Leu, Paul Atzberger |
Katie Bouman (Invited Talk 2) | |
Katie Bouman |
Alán Aspuru-Guzik (Invited Talk 3) | |
Alan Aspuru-Guzik |
Hamiltonian Graph Networks with ODE Integrators (Contributed Talk 3) | |
Alvaro Sanchez Gonzalez |
Lunch Break | |
Maria Schuld (Invited Talk 4) | |
Maria Schuld |
Lenka Zdeborova (Invited Talk 5) | |
Lenka Zdeborová |
Afternoon Coffee Break & Poster Session (Coffee Break) | |
Heidi Komkov, Stanislav Fort, Zhaoyou Wang, Rose Yu, Ji Hwan Park, Sam Schoenholz, Taoli Cheng, Ryan-Rhys Griffiths, Chase Shimmin, Surya Karthik Mukkavili, Philippe Schwaller, Christian Knoll, Andrew Sun, Keiichi Kisamori, Gavin Graham, Gavin Portwood, Hsin-Yuan Huang, Paul Novello, Moritz Munchmeyer, Anna Jungbluth, Daniel Levine, Ibrahim Ayed, Steven Atkinson, Jan Hermann, Peter Grönquist, , Priyabrata Saha, Nick Glaser, Lingge Li, Yutaro Iiyama, Rushil Anirudh, Maciej Koch-Janusz, Vikram Sundar, Francois Lanusse, Auralee Edelen, Jonas Köhler, Jacky Yip, jiadong guo, Xiangyang Ju, Adi Hanuka, Adrian Albert, Valentina Salvatelli, Mauro Verzetti, Javier Duarte, Eric Moreno, Emmanuel de Bézenac, Athanasios Vlontzos, Alok Singh, Thomas Klijnsma, Brad Neuberg, Paul Wright, Mustafa Mustafa, David Schmidt, Steven Farrell, Hao Sun |
Towards an understanding of wide, deep neural networks (Invited Talk 6) | |
Yasaman Bahri |
Learning Symbolic Physics with Graph Networks (Contributed Talk 4) | |
Miles Cranmer |
Metric Methods with Open Collider Data (Contributed Talk 5) | |
Eric Metodiev |
Equivariant Hamiltonian Flows (Contributed Talk 6) | |
Danilo Jimenez Rezende |