Organising Committee :

• Peter Battaglia, senior scientist at Google Deepmind,

• Anja Butter, ITP Heidelberg : generator models and uncertainties in ML for Particle Physics,

• Cécile Germain, Emeritus professor (computer science) Université Paris-Saclay, LRI-CNRS, and INRIA TAU team, organiser of the 2014 HiggsML and 2018-2019 TrackML challenge,

• Tobias Golling, associate professor at Université de Genève, generative models and anomaly detection for particle physics ,

• Vladimir Vava Gligorov,  CNRS/IN2P3 LPNHE,  leader of the LHCb Real Time analysis project, organiser of the Real Time Analysis Institut Pascal Workshop,

• Eilam Gross, Weizmann Institute, organiser of the Hammers and Nails 2017 and 2019 workshop,

• Michael Kagan, SLAC, co-coordinator of CERN Interexperiment Machine Learning group,

• Danilo Rezende, Researcher on Probabilistic Methods for Decision Making, Senior Staff Researcher and Team Lead at Google Deepmind

• David Rousseau,  CNRS/IN2P3 IJCLab : former co-coordinator of ATLAS Machine Learning group, co-coordinator of the LHC Interexperiment Machine Learning Group, organiser of the 2014 Higgs Machine Learning challenge, and of the 2018-2019 TrackML challenge,

• Andreas Salzburger, CERN,  coordinator of the ATLAS software upgrade group, organiser of the 2018-2019 TrackML challenge and organiser of the Advanced Pattern Recognition Institut Pascal Workshop,

• Savannah Thais, Princeton, representation learning for  Particle Physics, AI and ethics,

• Jean-Roch Vlimant,  Caltech, co-coordinator of CMS Machine Learning group, organiser of the 2018-2019 TrackML challenge,

• Slava Voloshynovskiy, head of Stochastic Information Processing group,  Université de Genève

Program Manager (Institut Pascal): Sabrina Soccard

Overall program  :

• Tue  19 - Wed 20 Apr : Workshop on Representation Learning from Heterogeneous/Graph-Structured Data
• Thu 21 Apr - Sat 23 Apr morning : Workshop on Dealing with Uncertainties 
• Mon 25  - Tue 26 : Workshop on Generative Models

• Wed 27 - Fri 29th : Learning to Discover  AI and Physics conference

Important dates

• 30th Nov 2021 : workshop application closed except on invitation by the organisers. It might be re-opened in Jan depending on the number of participants lost when rescheduling from Feb to April
• TBD : conference abstract submission closes (re-opening the conference abstract is being considered)
• TBD: acceptance notification for workshop participation and conference abstracts
• 19th Mar 2022 : conference registration closes for on-site participation

Pitch :

Learning To Discover is a program on Artificial Intelligence and High Energy Physics (HEP) to take place at Institut Pascal Paris-Saclay 19th Apr 2022 to 29th Apr 2022, in its beautiful new building. Over the two weeks, three themes will be successively tackled during innovation-oriented sessions of 2-3 days each, followed by a  three days general conference on AI and physics.

Confirmed speakers in the final conference

(being updated after rescheduling to April)

• Bertrand Braunschweig, Bi.LaB
• Bruce Denby, Institut Langevin ondes et images
• Francois Fleuret, Université Genève
• Alex Gramfort, INRIA Saclay
• Isabelle Guyon, Université Paris-Saclay and ChaLearn
• Balázs Kégl, Huawei France
• François Lanusse, CEA/IRFU Saclay
• Alistair Nolan, OECD
• Sofia Vallecorsa, CERN
• Gael Varoquaux, INRIA Saclay
• Max Welling, University of Amsterdam

Covid

Although many participants will be on-site, Institut Pascal is fully equipped with technology allowing remote participation as seamless as possible.  It can be anticipated that “pass sanitaire” (proof of vaccination (with booster "3rd dose" if full vaccination completed more than 7 months earlier) or negative test less than 24 hour ago) will be required for on-site participants. Masks wearing mandatory in the building. Exact rules to be obtained from the government official covid page.

Scope

Since 2014, the field of AI and HEP has grown exponentially. Physicists have realised quickly the potential of AI to deal with the large amount of complex data they are collecting and analysing. Many AI techniques have been put forward, with scientific collaboration based on open data sets, challenges, workshops and papers.

Learning To Discover is a first-of-its-kind program where participants will have access to deep technical insights in advanced machine learning techniques, and their application to particle physics. During the event, blending the concept of hackathon, hands-on and tutorials, physicists who have attempted to apply machine learning to specific challenges in HEP will expose their problem case and the solutions they have arrived at so far. ML experts will expose the latest advances in relevant techniques. Machine learning experts and ML-aware physicists will work hand in hand on existing datasets, building upon and improving existing solutions.Bibliography and open datasets will have been made available months earlier in order to make the event most productive. Under this particular environment, the participants will be able to discuss and understand shortcomings of existing solutions and develop novel architectures and methods to outperform on the specific problem. 
Three themes have tentatively been selected based on the one hand, their interest for HEP, and the fact there is already a number of HEP teams working on it, on the other hand, their importance in the Machine Learning field.

Representation Learning over Heterogeneous/Graph Data  workshop

HEP data are rarely image-like nor tabular. Despite promising applications of Graph Neural Network (GNN) to several HEP problems (tracking, classification, calorimeter reconstruction, particle flow, ...) there remains several bottlenecks towards getting models into production, in terms of both accuracy and inference speed. Multiple variants (Graph Attention Network, Transformers, ...) are available, with improved performance and resource requirements. The following topics are of interest: ways to extract information (at graph, node, or edge level), mechanisms for propagating information throughout the graph, generation of graph structure, evolution of graph topology within the model, etc...

Dealing with Uncertainties workshop 

Physicists ultimately write papers with measurements which always include an assessment of uncertainties. How to evaluate the uncertainty on a trained model ? How to build confidence into a ML model and how to convince our peers about it ? How to deal with the uncertainties on the input of the models to maximise the overall accuracy ? Bayesian Networks, Adversarial architectures and other techniques are being explored. 

Generative Models workshop

High Energy Physics is well known for having built accurate simulators which are able to deliver simulation of real experiments, from the Quantum Field Theory equations dealing with the interactions of fundamental particles up to specific answers of electronic circuits. These simulations are accurate, but not perfect, and very slow. Proof of Concept of using Generative Models (GAN, VAE,...) are being developed but many issues are to be solved before they make it to production. How to reach sufficient accuracy over a large parameter space ? How to make sure multi-dimension correlations are well described ?  How to deal with the irregularity of the detector (think of an image with pixels of different sizes and shapes) ?  
 

Physicists with concrete experience with Machine Learning (postdocs, advanced PhD students, ...) and Computer Scientists seasoned with the development of cutting edge ML models (expected participation from Google Deepmind, NVidia, IDIAP, ...) are invited to apply for attendance. Application is however open to everyone with experience and interest. The selection process will be as inclusive as possible, and only done so as to make the workshop fruitful for everyone and given the constraints of the premises.  The final general conference on AI and HEP is open to physicists and Computer Scientists until the maximum attendance is reached.

Learning to Discover : AI and High Energy Physics conference

The final conference will cover cutting edge topics in the field with keynote talks, summaries of the preceding workshops, as well as talks and posters from the call for contributions. 

Outlook

A special issue of Computing and Software for the Big Science (a refereed journal) will be prepared with the most relevant contributions with a submission deadline 4 months after the workshop, leaving ample time for finalisation of the studies showcased at the workshop. A number of workshops concerning AI and Physics have been organised in recent years, notably “Deep Learning for the Physical Science” at NeurIPS 2017 (https://dl4physicalsciences.github.io/), “Machine Learning and the Physical Science” at Neurips 2019, 2020 and 2021 (https://ml4physicalsciences.github.io) and “AI and physics” at AMLD 2020  and 2021 in Lausanne (https://appliedmldays.org/tracks/ai-physics). Studies developed at “Learning To Discover” will have a high chance at being accepted at future such events.