Learning to Discover

Session

AI and physics conference

CONF

27 avr. 2022, 09:00

Institut Pascal

Présidents de session

AI and physics conference: Day 1 Morning

• David Rousseau (IJCLab, Orsay, France)
• Jean-Roch Vlimant (California Institute of Technology (US))

AI and physics conference: Day 1 Afternoon

• Cécile Germain (LISN Université Paris-Saclay)
• Andreas Salzburger (CERN)

AI and physics conference: Day 2 morning

• François Lanusse (CEA Saclay)
• Eilam Gross (Weizmann)

AI and physics conference: Day 2 afternoon

• Savannah Thais (Princeton)

AI and physics conference: Day 3 Morning

• Pietro Vischia (UC Louvain)
• Jean-Roch Vlimant (California Institute of Technology (US))

AI and physics conference: Day 3 afternoon

• Anja Butter (ITP Heidelberg)
• Felice Pantaleo (CERN)

74. Conference Introduction from organisers

27/04/2022 09:00

80. Purely Data-Driven Approaches to Weather Prediction: Promise and Perils

Suman Ravuri (Deepmind)

27/04/2022 09:15

The use of machine learning (ML) models for weather prediction has emerged as a popular area of research. The promise of these models — whether in conjunction with more traditional Numerical Weather Prediction (NWP), or on its own — is that they allow for more accurate predictions of the weather at significantly reduced computational cost. In this talk, I will discuss both the promise and...

76. How to explain the success in scikit-learn and how to make it last

Alexandre Gramfort (INRIA)

27/04/2022 10:00

The scikit-learn software has now been cited more than 50000 times in 10 years. It's the most used software by machine learning experts on kaggle. One considers that about 2 millions of data scientists are using it every month. Yet this was made possible with limited resources and mostly by researchers and engineers in academia. In this talk I will first list the reasons that can explain this...

77. Origins of AI in High Energy Physics from Orsay to Chicago – and back!

Bruce Denby (ESPCI)

27/04/2022 11:00

The world’s first paper on AI in High Energy Physics was written right here in Orsay, 35 years ago. In this presentation, its author outlines the scientific contributions of the article and their impact; gives a historical account of how it came to be written; and presents an overview of what it was like working on AI in HEP in the early days of the field.

78. Summary of Dealing with Uncertainties workshop

Michael Aaron Kagan (SLAC)

27/04/2022 11:45

79. Data-centric AI

Romain Egele (Université Paris Saclay / Argonne National Laboratory)

27/04/2022 14:00

Data-Centric Artificial Intelligence (DCAI) was introduced by Andrew Ng in 2021. This call was launched to answer the discrepancy of research contributions which almost always focus on models while considering fixed and well engineered data. However, in practice data-scientists spend most of their time on data engineering tasks.
Through this presentation, we will start by giving a broad...

36. Application of Self-organizing maps in high energy physics

Kai Habermann (University of Bonn)

27/04/2022 14:30

Self-Organizing-Maps (SOM) are widely used neural nets for unsupervised learning and dimensional reduction. They have not yet been applied in high energy physics. We discuss two applications of SOM in particle physics. First, the separation of physics processes in regions of the dimensionally reduced representation. Second, we obtain Monta Carlo scale factors by fitting templates to the...

35. Super-resolution for calorimetry

Francesco Di Bello (INFN and U. of Rome)

27/04/2022 14:45

Super-resolution algorithms are commonly used to enhance the granularity of an imaging system beyond what can be achieved using the measuring device.
We show the first application of super-resolution algorithms using deep learning-based methods for calorimeter reconstruction using a simplified geometry consisting of overlapping showers originated by charged and neutral pions events.
The task...

28. Inducing selective posterior-collapse in variational autoencoders by modelling the latent space as a mixture of normal-gamma distributions

Emma JOUFFROY (CEA & IMS)

27/04/2022 15:00

Variational autoencoders are deep generative networks widely used for a large area of tasks, such as image or text generation. They are composed of two sub-models. On the one hand, the encoder aims to infer the parameters of the approximate posterior distribution $\mathcal{N}(z;x,\mu(\phi),\sigma(\phi))$ of a low dimensional latent vector $z$ that represents the generative factors of the input...

25. Deep Multi-task Mining Calabi-Yau Manifolds

Riccardo Finotello (CEA LIST, CEA ISAS)

27/04/2022 15:15

Computing topological properties of Calabi-Yau manifolds is a challenging mathematical task. Recent years have witnessed the rising use of deep learning as a method for exploration of large sets of data, to learn their [patterns and properties][1]. This is specifically interesting when it comes to unravel complicated geometrical structures, as well as in the development of trustworthy AI...

81. Scientific inference with imperfect theories: examples with machine learning and neurosciences

Gael Varoquaux (INRIA)

27/04/2022 16:00

Science has progressed by reasoning on what models could not predict because they were missing important ingredients. And yet without correct models, standard statistical methods for scientific evidence are not sound. I will argue that machine-learning methodology provides solutions to ground reasoning about empirically evidence more on models’ predictions, and less on their ingredients. I...

20. Study of model construction and the learning for hierarchical models

Masahiko Saito (International Center for Elementary Particle Physics, University of Tokyo)

27/04/2022 16:30

To efficiently solve a big problem by deep learning, it is sometimes useful to decompose it into smaller blocks, enabling us to introduce our knowledge into the model by utilizing an appropriate loss function for each block.
A simple model decomposition, however, causes a performance decrease due to bottlenecks of transferred information induced by the loss definition.
We proposed a method...

44. Uncertainty Aware Learning for High Energy Physics With A Cautionary Tale

Aishik Ghosh (UC Irvine)

27/04/2022 16:45

Machine learning tools provide a significant improvement in sensitivity over traditional analyses by exploiting subtle patterns in high-dimensional feature spaces. These subtle patterns may not be well-modeled by the simulations used for training machine learning methods, resulting in an enhanced sensitivity to systematic uncertainties. Contrary to the traditional wisdom of constructing an...

27. Graph Neural Networks for track reconstruction at HL-LHC

Alexis VALLIER (Laboratoire des 2 Infinis - Toulouse, CNRS / Univ. Paul Sabatier (FR))

27/04/2022 17:00

The physics reach of the HL-LHC will be limited by how efficiently the experiments can use the available computing resources, i.e. affordable software and computing are essential. The development of novel methods for charged particle reconstruction at the HL-LHC incorporating machine learning techniques or based entirely on machine learning is a vibrant area of research. In the past years,...

41. Particle Tracking with Graph Neural Networks

Gage DeZoort (Princeton University)

27/04/2022 17:15

Each proton-proton collision event at the LHC produces a myriad of particles and interactions that are recorded by specialized detectors. Trackers are designed to sample the trajectories of these particles at multiple space-points; tracking is the connecting-the-dots process of linking these signals (hits) to reconstruct particle trajectories (tracks). Tracker data is naturally represented as...

32. Jet Energy Corrections with GNN Regression

Daniel Holmberg (CERN)

27/04/2022 17:30

Accurate energy measurements of jets are crucial to many analyses in particle physics. To improve the performance of current jet energy corrections, machine learning based methods are investigated. Following recent developments in jet flavor classification, jets are considered as unordered sets of their constituent particles, referred to as particle clouds. In addition, particular care is...

83. Experiment optimisation with differentiable programming

Tommaso Dorigo (INFN Padova)

28/04/2022 09:00

In 2012 the imagenet challenge and the discovery of the Higgs boson produced a paradigm shift in particle physics analysis. Today a new revolution awaits to be made. The possibility to map continuously the space of design solutions of even the hardest optimization problem, using differentiable programming, promises to provide us with entirely new and more performant or cheaper solutions to...

42. Astronomical source separation with variational autoencoders

Biswajit Biswas (Laboratorie Astroparticule et cosmologie (APC))

28/04/2022 09:45

Upcoming surveys such as the Large Survey of Space and Time (LSST) and Euclid will observe the sky with unprecedented depth and area of coverage. As these surveys will detect fainter objects, the increase in object density will lead to an increased number of overlapping sources. For example, in LSST we expect around 60% of the objects to be blended. In order to better constrain Dark Energy...

29. Machine Learning for Real-Time Processing of ATLAS Liquid Argon Calorimeter Signals with FPGAs

Nairit SUR (CPPM - CNRS/IN2P3)

28/04/2022 10:00

The Phase-II upgrade of the LHC will increase its instantaneous luminosity by a factor of 7 leading to the High Luminosity LHC (HL-LHC). At the HL-LHC, the number of proton-proton collisions in one bunch crossing (called pileup) increases significantly, putting more stringent requirements on the LHC detectors electronics and real-time data processing capabilities.

The ATLAS Liquid Argon...

31. Looking for rare di-Higgs events at the LHC with Machine (Deep) Learning techniques

Brunella D'Anzi (Universita e INFN, Bari (IT))

28/04/2022 10:15

Artificial intelligence (AI) algorithms applied to HEP analyses come to the rescue in scenarios in which implementing an efficient discriminant for separating a very low-rate signal from a huge background is extremely important. In this context, we investigate the usage of several Machine Learning (ML) and Deep Learning (DL) methods via the TensorFlow open-source platform to boost the...

26. An Imperfect Machine to search for New Physics: dealing with uncertainties in a machine-learning based signal extraction

Gaia Grosso (CERN)

28/04/2022 11:00

New Physics Learning Machine (NPLM) is a novel machine-learning based strategy to detect data departures from the Standard Model predictions, with no prior bias on the nature of the new physics responsible for the discrepancy. The main idea behind the method is to build the log-likelihood-ratio hypothesis test by translating the problem of maximizing the log-likelihood-ratio into the...

22. Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference

Maxime Vandegar (SLAC National Accelerator Laboratory)

28/04/2022 11:30

We study the problem of retrieving a truth distribution from noisy observed data, often referred to as unfolding in High Energy Physics, which facilitates comparisons with theoretical predictions, and thus aids the process of scientific discovery. Our simulation-based inference technique, which we call Neural Empirical Bayes (NEB), combines Empirical Bayes, also known as maximum marginal...

16. Renormalized Mutual Information for Artificial Scientific Discovery

Leopoldo Sarra (Max Planck Institute Science of Light)

28/04/2022 11:45

We derive a well-defined renormalized version of mutual information that allows us to estimate the dependence between continuous random variables in the important case when one is deterministically dependent on the other. This is the situation relevant for feature extraction, where the goal is to produce allow-dimensional effective description of a high-dimensional system. Our approach enables...

84. Summary of Representation workshop

Savannah Thais

28/04/2022 12:00

85. The five walls of Artificial Intelligence

Bertrand Braunschweig (BiLaB)

28/04/2022 14:00

Artificial intelligence is advancing at a very rapid pace in both research and applications, and is raising societal questions that are far from being answered. But as it moves forward rapidly, it runs into what I call the five walls of AI. Any one of these five walls is capable of halting its progress, which is why it is essential to know what they are and to seek answers in order to avoid...

86. AI in science: the need to increase research productivity

Alistair Nolan (OECD)

28/04/2022 14:45

In recent years a number of scholars – mainly economists -have argued that the productivity of science may be stagnating, or even in decline. The claim is not that science is failing to advance, but rather that outputs require ever more inputs (to the extent that scientific output occurs in any discrete way). If true, the consequences of any slowdown in the productivity of science could be...

21. ALICE - non parametric and parametric models, dealing with uncertainty

Marian Ivanov (GSI Darmstadt and CERN)

28/04/2022 15:20

ALICE, one of the four big experiments at the CERN LHC, is a detector dedicated to heavy-ion physics. A high interaction rate environment causes pile-up which necessitates the use of advanced methods of data analysis.

Over the recent years machine learning (ML) has come to dominate multi-dimensional data analysis. However, it is more difficult to interpret the ML models and to evaluate...

34. Efficiency parametrization with Neural Networks

Nilotpal Kakati (Weizmann Institute of Science)

28/04/2022 15:35

An overarching issue of LHC experiments is the necessity to produce massive numbers of simulated collision events in very restricted regions of phase space. A commonly used approach to tackle the problem is the use of event weighting techniques where the selection cuts are replaced by event weights constructed from efficiency parametrizations. These techniques are however limited by the...

87. Highly accurate protein structure prediction with AlphaFold

Tim Green (Deepmind)

29/04/2022 09:00

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence — the structure prediction component of the ‘protein folding problem’ — has been an important open research problem for more than 50 years. AlphaFold, a novel...

24. Sampling high-dimensional posterior by Neural Score Matching

Benjamin Remy (CEA Saclay)

29/04/2022 09:45

We present a novel methodology to address many ill-posed inverse problems, by providing a description of the posterior distribution, which enables us to get point estimate solutions and to quantify their associated uncertainties. Our approach combines Neural Score Matching for learning a prior distribution from physical simulations, and a novel posterior sampling method based on an annealed...

33. Symbolic expression generation via VAE

Sergei Popov (Higher School of Economics), Dr Mikhail Lazarev (Higher School of Economics)

29/04/2022 10:00

There are many problems in physics, biology, and other natural sciences in which symbolic regression can provide valuable insights and discover new laws of nature. A widespread Deep Neural Networks don’t provide interpretable solutions. Meanwhile, symbolic expressions give us a clear relation between observations and the target variable. However, at the moment, there is no dominant solution...

38. Unbinned measurements in global SMEFT fits from machine learning

Jaco ter Hoeve (Nikhef / VU Amsterdam)

29/04/2022 10:15

Global interpretations of particle physics data in the context of the Standard Model Effective Field Theory (SMEFT) rely on the combination of a wide range of physical observables from many different processes. We present ongoing work towards the integration of unbinned measurements into such global SMEFT interpretations by means of machine learning tools. We use a deep-learning...

88. Merging Physical Models with Deep Learning for Cosmology

François Lanusse (CEA Saclay)

29/04/2022 11:00

With an upcoming generation of wide-field cosmological surveys, cosmologists are facing new and outstanding challenges at all levels of scientific analysis, from pixel-level data reduction to cosmological inference. As powerful as Deep Learning (DL) has proven to be in recent years, in most cases a DL approach alone proves to be insufficient to meet these challenges, and is typically plagued...

89. AI and the meaning crisis

Balazs Kegl (Huawei France)

29/04/2022 11:30

How to bring value into AI : Valuelessness is an inherent and proudly upheld feature of the scientific approach. It made it successful for modelling the material world and to keep our biases under control. I will argue that, at the same time, it is one of the main obstacles for developing true AI that can be seamlessly integrated in society. I will shed light on this argument through my...

23. Unsupervised Learning Likelihood functions of LHC results

Humberto Reyes González (University of Genoa)

29/04/2022 12:00

Due to their undoubting importance, the systematic publication of Full Likelihood Functions (LFs) of LHC results is a very hot topic among the HEP community. Major steps have been taken towards this goal; a notable example being ATLAS release of full likelihoods with the pyhf framework. However, the publication of LFs remains a difficult challenge since they are generally complex and...

39. Online-compatible unsupervised nonresonant anomaly detection

Dr Vinicius Mikuni (Lawrence Berkeley National Lab. (US))

29/04/2022 12:15

There is a growing need for anomaly detection methods that can broaden the search for new particles in a model-agnostic manner. Most proposals for new methods focus exclusively on signal sensitivity. However, it is not enough to select anomalous events—there must also be a strategy to provide context to the selected events. We propose the first complete strategy for unsupervised detection of...

99. Thanks to Sabrina and Aurélie

29/04/2022 12:30

90. Summary of Generator workshop

Johnny Raine (Université de Genève)

29/04/2022 14:00

91. Quantum Generative Models in High Energy Physics

Sofia Vallecorsa (CERN)

29/04/2022 14:30

Theoretical and algorithmic advances, availability of data, and computing power have opened the door to exceptional perspectives for application of classical Deep Learning in the most diverse fields of science, business and society at large, and notably in High Energy Physics (HEP). Generative models, in particular, are among the most promising approaches to analyse and understand the amount...

19. Quantum generative models for muonic force carriers events

Oriel Orphee Moira Kiss (CERN, UNIGE)

29/04/2022 15:00

Generative models (GM) are promising applications for near-term quantum computers due to the probabilistic nature of quantum mechanics. In this work, we propose comparing a classical conditional generative adversarial network (C-GAN) approach with a Born machine while addressing their strengths and limitations to generate muonic force carriers (MFCs) events. The former uses a neural network as...

18. ML-based Correction to Accelerate Geant4 Calorimeter Simulations

Dr Evangelos Kourlitis (Argonne National Laboratory)

29/04/2022 15:15

The Geant4 detector simulation, using full particle tracking (FullSim), is usually the most accurate detector simulation used in HEP but it is computationally expensive. The cost of FullSim is amplified in highly segmented calorimeters where large fraction of the computations are performed to track the shower’s low-energy photons through the complex geometry. A method to limit the production...

92. Advances in Machine Learning Based Modeling and Control of Particle Accelerators at Scientific User Facilities

Auralee Edelen (SLAC National Accelerator Lab)

29/04/2022 16:00

Particle accelerators are used in a wide array of medical, industrial, and scientific applications, ranging from cancer treatment to understanding fundamental laws of physics. While each of these applications brings with them different operational requirements, a common challenge concerns how to optimally adjust controllable settings of the accelerator to obtain the desired beam...

43. Simulating the LHCb experiment with Generative Models

Matteo Barbetti (University of Florence and INFN-Firenze)

29/04/2022 16:30

During Run 2 of the Large Hadron Collider at CERN, the LHCb experiment has spent more than 80% of the pledged CPU time to produce simulated data samples. The upcoming upgraded version of the experiment will be able to collect larger data samples, requiring many more simulated events to analyze the data to be collected in Run 3. Simulation is a key necessity of analysis to interpret signal vs...

30. Generative models uncertainty estimation

Nikita Kazeev (HSE)

29/04/2022 16:45

In recent years fully-parametric fast simulation methods based on generative models have been proposed for a variety of high-energy physics detectors. By their nature, the quality of data-driven models degrades in the regions of the phase space where the data are sparse. Since machine-learning models are hard to analyze from the physical principles, the commonly used testing procedures are...

40. Generative models for scalar field theories: how to deal with poor scaling?

Javad Komijani (ETH Zurich)

29/04/2022 17:00

The basis of lattice QCD is the formulation of the QCD path integral on a Euclidean
space-time lattice, allowing for computing expectation values of observables using Monte
Carlo simulations. Despite the success of lattice QCD in determinations of many parameters
of the Standard Model, limitations on the current techniques and algorithms still exist,
such as critical slowing down or the...

97. Conclusion from the organisers

David Rousseau (IJCLab, Orsay, France)

29/04/2022 17:15

75. TBA

82. TBA