Track / Overview

The interface between artificial intelligence (AI) and physics has seen a rapid expansion, with ground breaking advances in both the development and application of machine learning (ML) algorithms designed for domain specific physics problems, and the utilization of tools from physics to better understand theoretical aspects of machine learning. For instance, ML models have enabled signal identification in heterogeneous and 3D detector data, and simulator driven inference and anomaly detection in large and high dimensional datasets, e.g. at the Large Hadron Collider and at the LSST. ML models have also enabled high fidelity generative models as fast approximate simulators or as proposal distributions incorporating physics inductive bias for sampling from complex distributions in lattice QCD, particle scattering amplitudes, and many-body physics. At the same time, theoretical methods from statistical physics and quantum field theory have been applied to understanding neural network learning dynamics and finite network size behaviors.

The first installment of the AI & Physics track at AMLD2020 broadly examined the AI / Physics interface. The AI & Physics track at AMLD2021 will focus on specific subdomains that target improving physics data analysis with the tools of ML and understanding ML models with the tools of physics. The track will contain three sub-sessions covering (i) inference and anomaly detection, (ii) Statistical Physics for understanding ML, (iii) ML for quantum technologies. These topics address key questions of how AI can improve the capability to perform scientific measurements and identify spurious signatures that may be signs of new physical behavior, how ML in the high dimensional limit can be understood through the lens of theoretical physics, and how ML can inform the design and control of quantum experiments.

Machine learning and physics have a symbiotic and transformative influence on each other, leading to profound changes in approaches to physics and ML and thus paving the way to tackle previously intractable problems and to exploit new capabilities. The objective of covering these topics is on the one hand to investigate how ML can optimise the design, control, and information extraction of experiments and to speed up compute-intensive tasks which limit research capabilities. On the other, theoretical tools from physics provide a means to extract information about ML models and their learning dynamics. Thus this track aims to explore the questions: How can we best extract insights from physics data and make use of powerful physics models and high fidelity simulators whilst ensuring such methods are well calibrated? Can we harness the capabilities of ML to automate the delicate design and data collection of quantum experiments? Can we describe the dynamics of neural networks from a first principles understanding?

Track / Schedule


Opening remarks – ML for Quantum Physic

Machine Learning Simulation of Quantum Matter

With Giuseppe Carleo

Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States

With Agnes Valenti

Control of Stochastic Quantum Dynamics by Differentiable Programming

With Frank Schäfer

Optimized Observable Readout from Single-Shot Images of Ultracold Atoms via Machine Learning

With Paolo Molignini

Machine learning designing quantum experiments

With Alexey Melnikov

Poster Session

Lunch break

Opening remarks – ML and Statistical Physics

Dynamics of learning in simple neural networks through the lens of statistical physics

With Andrew Saxe

Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft Committee Machines

With Roman Worschech

Training is not a continuous search for a minimum

With Diego Tapias

Understanding classification problems using statistical physics: the role of data structure and losses

With Marylou Gabrié

Towards realistic data models for simple Machine Learning problems

With Bruno Loureiro

Coffee break

Opening remarks – Inference and Anomaly Detection Session

Deep Learning for molecular physics

With Frank Noe

Unsupervised anomaly detection as a new strategy for discoveries

With Gregor Kasieczka

Uncertainty Aware Learning for High Energy Physics

With Aishik Ghosh

Let's open the black box! Hessian-based toolbox for interpretable and reliable machines learning physics

With Anna Dawid

Uncertainty and Out-of-distribution Robustness in Deep Learning

With Balaji Lakshminarayanan

Concluding remarks

Track / Speakers

Alexey Melnikov

Head of Quantum Machine Learning, Terra Quantum AG

Giuseppe Carleo

EPFL assistant professor, head of the Computational Quantum Science Lab

Balaji Lakshminarayanan

Staff Research Scientist, Google Brain

Marylou Gabrié

Research Fellow, NYU & Flatiron Institute

Agnes Valenti

PhD Student, ETH

Bruno Loureiro

Scientist, EPFL

Gregor Kasieczka

Professor, Universität Hamburg

Anna Dawid

PhD Student, University of Warsaw & ICFO

Paolo Molignini

Postdoctoral Research Associate, University of Cambridge

Roman Worschech

PhD Student, Max Planck Institute

Diego Tapias

Postdoc, University of Göttingen

Aishik Ghosh

Postdoctoral Scholar, UC Irvine and LBNL

Frank Schäfer

PhD Student, University of Basel

Andrew Saxe

Associate Professor, UCL

Frank Noe

Professor, FU Berlin

Track / Co-organizers

Maurizio Pierini

Research Staff, CERN

Stefano Carrazza

Researcher, University of Milan

Slava Voloshynovskiy

Professor, University of Geneva

Tobias Golling

Professor, University of Geneva

Eliska Greplova

Postdoctoral Researcher, ETH Zurich

Michael Kagan

Lead Staff Scientist, SLAC / Stanford

Lenka Zdeborová

Professor, EPFL

Frédéric Dreyer

Postdoctoral Researcher, University of Oxford

David Rousseau

Senior Scientist, Université Paris-Saclay

AMLD EPFL 2021 / Tracks & talks

AI & Democracy

Robert West, Roy Gava, Victor Kristof, Steven Eichenberger, Alexandra Siegel, Lucas Leemann, Rayid Ghani, Sophie Achermann, Alexander Immer, Jacques Savoy, Oana Goga, Christine Choirat, Arianna Ornaghi, Irio Musskopf

10:00-18:00 January 25Online

AI & Food and Nutrition

Marcel Salathé, Fabio Mainardi, Tome Eftimov, Sharada Mohanty, Philippe Glénat, Timon Zimmermann, Mireille Moser, Ugo Gentile, Christoph Trattner, Enrico Zio, Yamine Bouzembrak, Christian Nils Schwab, Carrol Plummer, Patrizia Catellani, Matthias Graeber, Lorijn van Rooijen, Kristina Gligorić, Lydia Afman, Nourchene Ben Romdhane, Talia Salzmann, Thomas Chen, Gjorgjina Cenikj, Gorjan Popovski, Sola Shirai

09:00-17:00 March 01Online

Clinical Machine Learning

Marcel Salathé, Bastian Rieck, Matteo Togninalli, Damian Roqueiro, Christian Bock, Daniel Rueckert, Michael Menden, Stephanie Hyland, Steve Jiang, Danielle Belgrave, Julia Vogt, Tobias Gass, Alistair Johnson, Assaf Gottlieb, Finale Doshi-Velez, Bernice Elger, Vanessa Schumacher

09:10-18:00 March 18Online

AMLD / Global partners