PHYSTAT - Statistics meets ML

Session

Talks

10 Sept 2024, 09:00

Lecture Theatre 2, Blackett Laboratory (Imperial College London)

Conveners

Talks

• Wouter Verkerke (Nikhef National institute for subatomic physics (NL))

Talks

• Alan Heavens

Talks

• Sergei Gleyzer (University of Alabama (US))

Talks

• Robert Cousins Jr

Talks

• Daniel Mortlock

Talks

• Olaf Behnke (Deutsches Elektronen-Synchrotron (DE))

Talks

• Ryan James Nichol (UCL)

Talks

• Glen Cowan (Royal Holloway, University of London)

Talks

• David A. van Dyk (Imperial College London)

Talks

• Jason McEwen

Talks

• Kaisey Mandel (University of Cambridge)

Talks

• Lydia Brenner (Nikhef National institute for subatomic physics (NL))

13. Welcome

10/09/2024, 09:00

14. ML in Particle Physics

Gregor Kasieczka (Hamburg University (DE))

10/09/2024, 09:15

Machine learning and AI have quickly turned into indispensable tools for modern particle physics. They both greatly amplify the power of existing techniques - such as supercharging supervised classification - and enable qualitatively new ways of extracting information - such as anomaly detection and likelihood-free inference. Accordingly, the underlying statistical machinery needs to be...

111. Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

Jonas Spinner

10/09/2024, 10:00

Contributed Talk

Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architecture for high-energy physics. L-GATr represents high-energy data in a geometric algebra over four-dimensional space-time and is equivariant under...

15. Cosmology and machine learning

Ben Wandelt

10/09/2024, 11:00

Cosmologists strive to uncover the mysteries of the origin, composition, evolution, and fate of the cosmos from all the information the sky has to offer: the cosmic microwave background, galaxy surveys, exploding stars, and reverberations of space-time caused by colliding black holes and neutron stars. I will discuss new ways to connect cosmological theory and simulation with these data sets....

16. Simulation-based machine learning for gravitational-wave analysis

Maximilian Dax

10/09/2024, 11:45

Gravitational waves (GWs) provide a unique window to the universe, enabling us to study mergers of black holes and/or neutron stars. In my talk, I will highlight how machine learning can address critical limitations in GW data analysis. I will present key innovations in this field, driven by unusually high requirements for accuracy, reliability and interpretability. Finally, I will discuss how...

18. Interpretable Machine Learning for Particle Physics

Jesse Thaler (MIT/IAIFI)

10/09/2024, 14:00

The term "interpretability" encompasses various strategies to scrutinize the decisions made by machine learning algorithms. In this talk, I argue that interpretability, at least in the context of particle physics, should be considered as part of the broader goal of assessing systematic uncertainties. I provide examples from my own research on jet physics at the Large Hadron Collider, where...

19. Understanding and mitigating failures in anomaly detection: a probabilistic perspective

Lily Zhang

10/09/2024, 14:45

In this talk, we present an overview of anomaly detection from a probabilistic machine learning perspective, with a focus on work emerging from the machine learning literature. First, we discuss empirical failures of deep generative models for anomaly detection and why they occur, as well as their implications for deep generative modeling and anomaly detection. Then, we discuss the endeavor of...

21. Statistical tests for anomaly detection at the LHC

Gaia Grosso

10/09/2024, 16:00

Signal-agnostic data exploration could unveil very subtle statistical deviations of collider data from the expected Standard Model of particle physics. However, the extreme size, rate and complexity of the datasets generated at the Large Hadron Collider (LHC) pose unique challenges for data analysis. Making assumptions about what is relevant becomes unavoidable to scale the information down to...

22. Detecting New Physics as data anomalies at the LHC: Transitioning from small-scale toy datasets to millions of complex proton collisions

Thea Aarrestad (ETH Zurich (CH))

10/09/2024, 16:45

Anomaly detection has emerged as a promising technique for identifying subtle New Physics signals amidst a dominant Standard Model background. Due to the novelty of these techniques, they are often proposed and demonstrated on toy datasets that mimic real LHC data before being deployed in actual experiments. In this talk, we will discuss the challenges encountered during the transition from...

113. Anomaly aware machine learning for dark matter direct detection at the DARWIN experiment

Andre Joshua Scaffidi

10/09/2024, 17:10

Contributed Talk

This talk presents a novel approach to dark matter direct detection using anomaly-aware machine learning techniques in the DARWIN next-generation dark matter direct detection experiment. I will introduce a semi-unsupervised deep learning pipeline that falls under the umbrella of generalized Simulation-Based Inference (SBI), an approach that allows one to effectively learn likelihoods straight...

143. Feldman-Cousins’ ML Cousin

Joshua Villarreal

10/09/2024, 17:35

Contributed Talk

The statistical treatment of sterile neutrino searches suffers from the fact that Wilks’ theorem, a beneficial simplifying assumption, does not hold across all regions of parameter space. The alternative, the Feldman-Cousins algorithm, suffers from expensive computational run times that prohibit its application into many-experiment global fits. This contribution introduces a deep...

23. Theoretical and Societal Topics in AI and Deep Learning for Physicists

Pierre Baldi

11/09/2024, 09:00

I plan to touch on several theoretical topics (overparameterization, neural balance, attention and transformers) and their applications in physics and end on a proposal to solve some of the societal issues raised by AI inspired by physics.

24. AI Benchmarks and Science

Jeyan Thiyagalingam (Rutherford Appleton Laboratory, Science and Technology Facilities Council)

11/09/2024, 09:45

112. Improved Weak Lensing Photometric Redshift Calibration via StratLearn and Hierarchical Modeling

Maximilian Autenrieth (Imperial College London)

11/09/2024, 10:10

Contributed Talk

Discrepancies between cosmological parameter estimates from cosmic shear surveys and from recent Planck cosmic microwave background measurements challenge the ability of the highly successful ΛCDM model to describe the nature of the Universe. To rule out systematic biases in cosmic shear survey analyses, accurate redshift calibration within tomographic bins is key. In this work, we improve...

25. Simulation-based Inference (SBI)

Aishik Ghosh (University of California Irvine (US))

11/09/2024, 11:00

A powerful class of statistical inference methods are starting to be used in across fields that leverage the power of machine learning (ML) to perform inference directly from high-dimensional data. They can be used, for instance, to estimate fundamental physics parameters from data collected in high energy physics experiments, or cosmological / astrophysics observations and work with both...

114. Extending Unfolding Methods With Machine Learning

Vinicius Mikuni (LBL)

11/09/2024, 11:45

Correcting experimental measurements for detector effects, or unfolding, is a standard technique used at the LHC to report multi-differential cross section measurements. These techniques rely on binned data and are limited to low dimensional observables. In this talk, I will cover recent ideas to extend standard methods of unfolding using machine learning, enabling the measurements of ...

141. Generative Unfolding

Tilman Plehn (Heidelberg University)

11/09/2024, 14:00

Looking for a way modern machine learning transforms LHC physics, unfolding has for a long time been one of our goal, and only modern networks allow us to do this meaningfully. It does not only make analyses with a wide range of theory hypotheses more efficient, it also allows the LHC collaborations to publish their data. I will show how generative networks can be used for this purpose,...

29. lsbi: linear simulation based inference

Dr William Handley

11/09/2024, 14:25

Contributed Talk

Simulation-based inference is undergoing a renaissance in statistics and machine learning. With several packages implementing the state-of-the-art in expressive AI [mackelab/sbi] [undark-lab/swyft], it is now being effectively applied to a wide range of problems in the physical sciences, biology, and beyond.

Given the rapid pace of AI/ML, there is little expectation that the implementations...

31. Robust signal detection with classifiers decorrelated via optimal transport

Dr Purvasha Chakravarti (UCL)

11/09/2024, 14:50

New physics searches are usually done by training a supervised classifier to separate a signal model from the known Standard Model physics (also called the background model). However, even when the signal model is correct, systematic errors in the background model can influence supervised classifiers and might adversely affect the signal detection procedure. To tackle this problem, one...

115. The statistics of deep generative models for the LHC

Ramon Winterhalder (UCLouvain)

11/09/2024, 15:15

In recent years, deep generative models (DGMs) have become essential for various steps in the LHC simulation and analysis chain. While there are many types of DGMs, no Swiss-army-knife architecture exists that can effectively handle speed, precision, and control simultaneously. In this talk, I will explore different DGMs, outline their strengths and weaknesses, and illustrate typical...

142. Fairness Methods in Particle Physics Event Classification

Oliver Rieger (Nikhef National institute for subatomic physics (NL))

11/09/2024, 16:30

Contributed Talk

In social sciences, fairness in Machine Learning (ML) comprises the attempt to correct or eliminate algorithmic bias of gender, ethnicity, or sexual orientation from ML models. Many high-energy physics (HEP) analyses that search for a resonant decay of a particle employ mass-decorrelated event classifiers, as the particle mass is often used to perform the final signal extraction fit. These...

33. Systematics: Misery or Muse?

Kyle Stuart Cranmer (University of Wisconsin Madison (US))

11/09/2024, 16:55

Systematic uncertainties usually have a negative connotation since they reduce the sensitivity of an experiment. However, the practical and conceptual challenges posed by various types of systematic uncertainty also have a long track record of motivating new ideas. I will outline some examples for my own career where systematics were my muse for innovation.

116. Development of systematic-aware neural network trainings for binned-likelihood-analyses at the LHC

Artur Monsch (KIT - Karlsruhe Institute of Technology (DE))

11/09/2024, 17:40

Contributed Talk

We demonstrate a neural network training, capable of accounting for the effects of systematic variations of the utilized data model in the training process and describe its extension towards neural network multiclass classification. We show the importance of adjusting backpropagation to be able to handle derivatives of histogram bins during training and add an interpretation of the...

34. Model misspecification meets ML: a HEP perspective

Alexander Held (University of Wisconsin Madison (US))

12/09/2024, 09:00

The field of high energy physics (HEP) benefits immensely from sophisticated simulators and data-driven techniques to perform measurements of nature at increasingly higher precision. Using the example of HEP, I will describe how and where uncertainties are incorporated into data analysis to address model misspecification concerns. My focus will be how machine learning (ML), in the variety of...

35. Learned harmonic mean estimation of the Bayesian evidence with normalizing flows

Alicja Polanska (University College London)

12/09/2024, 09:45

Contributed Talk

Computing the Bayesian evidence is an important task in Bayesian model selection, providing a principled quantitative way to compare models. In this work, we introduce normalizing flows to improve the learned harmonic mean estimator of the Bayesian evidence. This recently presented estimator leverages machine learning to address the exploding variance problem associated with the original...

39. Interpretability in Semi-Supervised Classifier Tests for Model-Independent Searches of New Physics

Mikael Kuusela (Carnegie Mellon University (US))

12/09/2024, 10:45

Many model-independent search methods can be understood as performing a high-dimensional two-sample test. The test is typically performed by training a neural network over the high-dimensional feature space. If the test indicates a significant deviation from the background, it would be desirable to be able to characterize the "signal" the network may have found. In this talk, I will describe...

36. pop-cosmos: investigating the explainability of a high-dimensional, data-driven generative model in cosmology

Hiranya Peiris

12/09/2024, 11:15

I will present a perspective that explainability — model interrogation and validation rooted in domain knowledge — is a more important desideratum in fundamental science than interpretability in its strict meaning. In order to illustrate this point, I will draw on our recent work on pop-cosmos: a forward modelling framework for photometric galaxy survey data, where galaxies are modelled as...

37. Identifying Tau Neutrinos in IceCube

Philipp Eller (Wisconsin)

12/09/2024, 11:45

Astrophysical tau neutrinos were predicted for a long time, but only recently has IceCube been able to identify those at the 5 sigma significance level. The key to this discovery was using machine learning methods to analyse the data. In this talk, I will first give a brief overview of the analysis and results before we dive deeper into the neural nets. We will try to understand how they work...

38. Conditional generation

Tobias Golling (Universite de Geneve (CH))

12/09/2024, 12:10

“If you can simulate it, you can learn it.” The concept of conditional generation is powerful and versatile. The heavy lifting is distributed over a generator of a latent distribution of interest and an embedding network to encode the information contained in the data. Concrete applications to the reconstruction of neutrino kinematics in LHC collisions and associated interpretability...

41. Highlights, ML

Gilles Louppe, Gilles Louppe

12/09/2024, 14:00

40. Highlights, Statistics

Mikael Kuusela (Carnegie Mellon University (US))

12/09/2024, 14:45

42. Highlights, Astro/Cosmo

Luisa Lucie-Smith

12/09/2024, 16:00

43. Highlights, Particle Physics

Lukas Alexander Heinrich (Technische Universitat Munchen (DE))

12/09/2024, 16:45

44. Closing discussion

12/09/2024, 17:30

28. [Contributed talk]

27. [Contributed talk]

26. [Contributed talk]

17. [Contributed talk]

20. Anomalies

Lily Zhang

9. Astro/Cosmology for others

Lucas Makinen (Imperial College London)

30. Fairness Methods in Particle Physics Event Classification

Oliver Rieger (Nikhef National institute for subatomic physics (NL))

Contributed Talk

In social sciences, fairness in Machine Learning (ML) comprises the attempt to correct or eliminate algorithmic bias of gender, ethnicity, or sexual orientation from ML models. Many high-energy physics (HEP) analyses that search for a resonant decay of a particle employ mass-decorrelated event classifiers, as the particle mass is often used to perform the final signal extraction fit. These...

32. Feldman-Cousins’ ML Cousin

Josh Villarreal

Contributed Talk

The statistical treatment of sterile neutrino searches suffers from the fact that Wilks’ theorem, a beneficial simplifying assumption, does not hold across all regions of parameter space. The alternative, the Feldman-Cousins algorithm, suffers from expensive computational runtimes that prohibit its application into many-experiment global fits. This contribution introduces a deep learning-based...

8. Intro to ML (Speaker TBC)

7. Intro to statistics (Speaker TBC)

10. ML in Astro/Cosmology (speaker TBC)

12. ML in Particle Physics

Jonathon Mark Langford (Imperial College (GB))

11. Particle physics for others

Daniel Winterbottom (Imperial College (GB))