ML4Jets2025

Session

Theory

21 Aug 2025, 11:20

CHEN100 (California Institute of Technology)

Conveners

Theory

• Rikab Gambhir (MIT)

Theory

• Prasanth Shyamsundar (Fermi National Accelerator Laboratory)

25. Autonomous Model Building with Reinforcement Learning: An Application with Lepton Flavor Symmetries

Jake Rudolph (UC Irvine)

21/08/2025, 11:20

To explain Beyond the Standard Model phenomena, a physicist has many choices to make in regards to new fields, internal symmetries, and charge assignments, collectively creating an enormous space of possible models. We describe the development and findings of an Autonomous Model Builder (AMBer), which uses Reinforcement Learning (RL) to efficiently find models satisfying specified discrete...

35. Observable Optimization for Precision Theory: Machine Learning Energy Correlators

Katherine Fraser (Harvard University)

21/08/2025, 11:40

The practice of collider physics typically involves the marginalization of multi-dimensional collider data to one-dimensional observables. In many cases, the observable can be arbitrarily complicated, such as the output of a neural network. However, for precision measurements, the observable must correspond to something computable. In this work, we demonstrate that precision-theory-compatible...

45. Giving machine learning a boost towards respecting (approximate) symmetries

Inbar Savoray (UC Berkeley)

21/08/2025, 12:00

In the physical sciences, symmetries provide powerful inductive biases from theoretical insights. Incorporating these constraints into the training of machine learning models is expected to improve robustness and lead to more data-efficient models that are easier to interpret. However, fully equivariant models can be difficult to train and implement. Moreover, real-world experiments often...

96. An Energy Correlation Function tagger for gluon-gluon resonances

Connor Moore (University of Notre Dame (US))

21/08/2025, 12:20

In this talk, we present a gluon-gluon resonance tagger using Energy Correlation Functions evaluated on large-radius jets. We discuss the performance in simulation and also assess the ability of simulation to accurately model high-point correlator functions in data.

53. Explicit versus implicit physics priors for separating nearly identical classes

Tanvi Wamorkar (Lawrence Berkeley National Lab. (US))

22/08/2025, 09:00

Machine learning in high energy physics has been accelerated due to two key developments: equivariant models which encode prior knowledge about the symmetries present in high energy physics datasets and models that are pretrained to perform similar tasks on large datasets, encoding useful domain knowledge. In this work, we explore the fundamental tradeoff between explicitly incorporating...

67. Machine Learning Neutrino-Nucleus Cross Sections [remote]

Dr Karla Tame-Narvaez (Fermilab National Accelerator Laboratory)

22/08/2025, 09:20

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section— leveraging Standard Model symmetries— can be learned...

73. A novel loss function to optimise signal significance in particle physics [remote]

Jai Bardhan

22/08/2025, 09:40

We construct a surrogate loss to directly optimise the significance metric used in particle physics. We evaluate our loss function for an event classification task and show that it produces decision boundaries that change according to the cross sections of the processes involved. We find that the models trained with the new loss have higher signal efficiency for similar values of estimated...

80. Machine Learning Symmetries in Physics from First Principles

Konstantin Matchev (University of Alabama (US))

22/08/2025, 10:00

Symmetries are the cornerstones of modern theoretical physics, as they imply fundamental conservation laws. The recent boom in AI algorithms and their successful application to high-dimensional large datasets from all aspects of life motivates us to approach the problem of discovery and identification of symmetries in physics as a machine-learning task. In a series of papers, we have developed...