arXiv subjects

Daniel Whiteson

Publications and source records attributed to Daniel Whiteson.

At least 19 recordsLinked to original sources

arXiv2026

Towards Engineering Scaling Laws with Pretraining Data Composition

Neural scaling laws describe how model performance improves as a power law in compute, model size, and dataset size. While well-established for large language models, these relationships are emerging for large models in particle physics. As with language, empirical studies show that the performance scales as a power law. However, unlike natural language or image domains, fundamental physics has high-fidelity simulators that produce synthetic data cheaply. This favors scaling regimes where additional data is cheaper than additional parameters, and allows the pretraining dataset itself to be engineered to influence the scaling. For the task of classifying hadronic jets produced in collisions of high-energy particle beams, we show that the scaling behavior can be engineered towards requiring more data rather than larger models by inclusion of pretraining data which is more diverse and better aligned with the downstream classification task.

hep-ex↗

arXiv2026

Time-dependent signals of new physics at the LHC

The Large Hadron Collider (LHC) is sensitive to signals of beyond the Standard Model physics through a variety of channels including missing energy and resonance searches. In most searches, the new physics and the Standard Model backgrounds are assumed to be invariant in time, up to systematic effects from the experiment. However, new physics with a time variation would provide an additional handle to separate signal from background. Such a time variation may come from ultralight dark matter coupling to an oscillating background field. In this paper, we consider an interaction of dark matter with quarks and an additional heavy particle, and show that the sensitivity of a search that uses timing information at the LHC can be up to a factor of two stronger compared to one that does not use time information.

hep-ph↗

arXiv2026

Explicit or Implicit? Encoding Physics at the Precision Frontier

High-performance machine learning tools in particle physics rest on two complementary directions: encoding symmetries explicitly in the architecture, and implicitly learning the structure of the data through large-scale (pre-) training. We compare the performance of the representative L-GATr and OmniLearn models on three especially challenging tasks: reweighting-based unfolding, likelihood-ratio estimation, and weakly supervised anomaly detection. Across all benchmarks, both methods achieve comparable performance given the statistical precision of the finetuning datasets, suggesting that the significant efficiency gains from encoding known particle physics structures are largely method-independent.

hep-ph↗

arXiv2025

Generative Unfolding of Jets and Their Substructure

Unfolding, for example of distortions imparted by detectors, provides suitable and publishable representations of LHC data. Many methods for unbinned and high-dimensional unfolding using machine learning have been proposed, but no generative method scales to the several hundred dimensions necessary to fully characterize LHC collisions. This paper proposes a 3-stage generative unfolding framework that is capable of unfolding several hundred dimensions. It is effective to unfold the jet-level kinematics as well as the full substructure of light-flavor jets and of top jets, and is the first generative unfolding study to achieve high precision on high-dimensional jet substructure.

hep-ph↗

arXiv2025

Characterizing Heavy Neutral Leptons: Measuring Parameters, Discriminating Majorana versus Dirac, and Using FASER2 as a Trigger for ATLAS

This work explores the potential of the proposed FASER2 experiment at the LHC to determine the properties of a discovered heavy neutral lepton (HNL), including its mass, couplings, and whether it is a Majorana or Dirac fermion. We first consider a Majorana HNL with mass $m_N = 1.84\,\rm{GeV}$ that is primarily produced through decays $D \to \mu N$ at the ATLAS interaction point. Such HNLs may travel macroscopic distances in the far-forward direction and then decay, yielding approximately 8600 $N \to \mu \pi$ decays in FASER2 at the High-Luminosity LHC. With FASER2 measurements alone, the HNL's mass and couplings can be measured to fractional uncertainties of approximately 0.1% and 3% at 95% CL, respectively, and the Dirac fermion hypothesis can be rejected at 99.8% CL. We then consider a second, more difficult, case of a Majorana HNL with mass $m_N = 2.00\,\rm{GeV}$, yielding only 80 $N \to \mu \pi$ decays in FASER2. With FASER2 alone, measurements of HNL properties are still possible, but somewhat less precise. However, by using FASER2 as a trigger for ATLAS and measuring the charge of the muon produced in association with the HNL at ATLAS to search for lepton number violation, one can precisely measure the HNL's properties and reject the Dirac fermion hypothesis at 99.7% CL. These results show that FASER2, sometimes in coordination with ATLAS, can precisely determine HNL properties, with far-reaching implications for our understanding of neutrino masses, baryogenesis, and the fundamental symmetries of nature.

hep-ph↗

arXiv2025

Efficient Estimation of Unfactorizable Systematic Uncertainties

Accurate assessment of systematic uncertainties is an increasingly vital task in physics studies, where large, high-dimensional datasets, like those collected at the Large Hadron Collider, hold the key to new discoveries. Common approaches to assessing systematic uncertainties rely on simplifications, such as assuming that the impact of the various sources of uncertainty factorizes. In this paper, we provide realistic example scenarios in which this assumption fails. We introduce an algorithm that uses Gaussian process regression to estimate the impact of systematic uncertainties \textit{without} assuming factorization. The Gaussian process models are enhanced with derivative information, which increases the accuracy of the regression without increasing the number of samples. In addition, we present a novel sampling strategy based on Bayesian experimental design, which is shown to be more efficient than random and grid sampling in our example scenarios.

stat.ME↗

arXiv2025

Finding Unexpected Non-Helical Tracks

Many theories of physics beyond the Standard Model predict particles with non-helical trajectories in a uniform magnetic field, but standard tracking algorithms assume helical paths and so are incapable of discovering non-helical tracks. While alternative algorithms have been developed for specific trajectories, unforeseen physics could lead to unanticipated behavior, and such unexpected tracks are largely invisible to current algorithms, despite being potentially striking to the naked eye. A model-agnostic tracking algorithm is presented, capable of reconstructing a broad class of smooth non-helical tracks without requiring explicit specification of particle trajectories, instead defining the target trajectories implicitly in the training sample. The network exhibits strong performance, even outside of the trajectories defined by the training sample. This proof-of-principle study takes the first step towards searches for unexpected tracks which may await discovery in current data.

hep-ex↗

arXiv2025

On Focusing Statistical Power for Searches and Measurements in Particle Physics

Particle physics experiments rely on the (generalised) likelihood ratio test (LRT) for searches and measurements, which consist of composite hypothesis tests. However, this test is not guaranteed to be optimal, as the Neyman-Pearson lemma pertains only to simple hypothesis tests. Any choice of test statistic thus implicitly determines how statistical power varies across the parameter space. An improvement in the core statistical testing methodology for general settings with composite tests would have widespread ramifications across experiments. We discuss an alternate test statistic that provides the data analyzer an ability to focus the power of the test on physics-motivated regions of the parameter space. We demonstrate the improvement from this technique compared to the LRT on a Higgs $\rightarrow\tau\tau$ dataset simulated by the ATLAS experiment and a dark matter dataset inspired by the LZ experiment. We also employ machine learning to efficiently calibrate critical values for a family of tests, which are then inverted to obtain statistically valid confidence intervals.

hep-ph↗

arXiv2025

Towards AI-assisted Neutrino Flavor Theory Design

Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast landscape of model-building possibilities. A model's construction typically relies on the intuition of theorists. It also requires considerable effort to identify appropriate symmetry groups, assign field representations, and extract predictions for comparison with experimental data. We develop an Autonomous Model Builder (AMBer), a framework in which a reinforcement learning agent interacts with a streamlined physics software pipeline to search these spaces efficiently. AMBer selects symmetry groups, particle content, and group representation assignments to construct viable models while minimizing the number of free parameters introduced. We validate our approach in well-studied regions of theory space and extend the exploration to a novel, previously unexamined symmetry group. While demonstrated in the context of neutrino flavor theories, this approach of reinforcement learning with physics software feedback may be extended to other theoretical model-building problems in the future.

hep-ph↗

arXiv2025

Fast and Precise Track Fitting with Machine Learning

Efficient and accurate particle tracking is crucial for measuring Standard Model parameters and searching for new physics. This task consists of two major computational steps: track finding, the identification of a subset of all hits that are due to a single particle; and track fitting, the extraction of crucial parameters such as direction and momenta. Novel solutions to track finding via machine learning have recently been developed. However, track fitting, which traditionally requires searching for the best global solutions across a parameter volume plagued with local minima, has received comparatively little attention. Here, we propose a novel machine learning solution to track fitting. The per-track optimization task of traditional fitting is transformed into a single learning task optimized in advance to provide constant-time track fitting via direct parameter regression. This approach allows us to optimize directly for the true targets, i.e., the precise and unbiased estimates of the track parameters. This is in contrast to traditional fitting, which optimizes a proxy based on the distance between the track and the hits. In addition, our approach removes the requirement of making simplifying assumptions about the nature of the noise model. Most crucially, in the simulated setting described here, it provides more precise parameter estimates at a computational cost over 1,000 times smaller, which leads directly to improvements in particle momentum estimation, vertex finding, jet substructure, and anomaly detection.

hep-ex↗

arXiv2025

Untangling New Physics in Single Resonant Top Quarks

Collisions of particles at the energy frontier can reveal new particles and forces via localized excesses. However, the initial observation may be consistent with a large variety of theoretical models, especially in sectors with new top quark partners, which feature a rich set of possible underlying interactions. We explore the power of the LHC dataset to distinguish between models of the singly produced heavy top-like quark which interacts with the Standard Model through an electromagnetic form factor. We study the heavy top decay to a top quark and a virtual photon which produces a pair of fermions, propose a technique to disentangle the models, and calculate the expected statistical significance to distinguish between various hypotheses.

hep-ph↗

arXiv2024

Learning Broken Symmetries with Approximate Invariance

Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized dataset, and is broken in actual data, due to asymmetries in the detector, or varying response resolution as a function of particle momentum. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the full, broken symmetry, effectively overconstraining the response of the neural network. We propose a learning model which balances the generality and asymptotic performance of unconstrained networks with the rapid learning of constrained networks. This is achieved through a dual-subnet structure, where one network is constrained by the symmetry and the other is not, along with a learned symmetry factor. In a simplified toy example that demonstrates violation of Lorentz invariance, our model learns as rapidly as symmetry-constrained networks but escapes its performance limitations.

hep-ph↗

arXiv2024

Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks

The production of multiple Higgs bosons at the CERN LHC provides a direct way to measure the trilinear and quartic Higgs self-interaction strengths as well as potential access to beyond the standard model effects that can enhance production at large transverse momentum $p_{\mathrm{T}}$. The largest event fraction arises from the fully hadronic final state in which every Higgs boson decays to a bottom quark-antiquark pair ($b\bar{b}$). This introduces a combinatorial challenge known as the \emph{jet assignment problem}: assigning jets to sets representing Higgs boson candidates. Symmetry-preserving attention networks (SPA-Nets) have been been developed to address this challenge. However, the complexity of jet assignment increases when simultaneously considering both $H\rightarrow b\bar{b}$ reconstruction possibilities, i.e., two "resolved" small-radius jets each containing a shower initiated by a $b$-quark or one "boosted" large-radius jet containing a merged shower initiated by a $b\bar{b}$ pair. The latter improves the reconstruction efficiency at high $p_{\mathrm{T}}$. In this work, we introduce a generalization to the SPA-Net approach to simultaneously consider both boosted and resolved reconstruction possibilities and unambiguously interpret an event as "fully resolved'', "fully boosted", or in between. We report the performance of baseline methods, the original SPA-Net approach, and our generalized version on nonresonant $HH$ and $HHH$ production at the LHC. Considering both boosted and resolved topologies, our SPA-Net approach increases the Higgs boson reconstruction purity by 57--62\% and the efficiency by 23--38\% compared to the baseline method depending on the final state.

hep-ph↗

arXiv2024

Fast multi-geometry calorimeter simulation with conditional self-attention variational autoencoders

The simulation of detector response is a vital aspect of data analysis in particle physics, but current Monte Carlo methods are computationally expensive. Machine learning methods, which learn a mapping from incident particle to detector response, are much faster but require a model for every detector element with unique geometry. Complex geometries may require many models, each with their own training samples and hyperparameter tuning tasks. A promising approach is the use of geometry-aware models, which condition the response on the geometry, but current efforts typically require cumbersome full geometry specification. We present a geometry-aware model that takes advantage of the regularity of detector segments, requiring only the definition of cell sizes across regular segments. This model outperforms the current state of the art by over 70% across several key metrics including the Wasserstein distance metric.

hep-ex↗

arXiv2024

Learning to Reconstruct Quirky Tracks

Analysis of data from particle physics experiments traditionally sacrifices some sensitivity to new particles for the sake of practical computability, effectively ignoring some potentially striking signatures. However, recent advances in ML-based tracking allow for new inroads into previously inaccessible territory, such as reconstruction of tracks which do not follow helical trajectories. This paper presents a demonstration of the capacity of ML-based tracking to reconstruct the oscillating trajectories of quirks. The technique used is not specific to quirks, and opens the door to a program of searching for many kinds of non-standard tracks.

hep-ex↗

arXiv2024

Hadronic Mono-$W'$ Probes of Dark Matter at Colliders

Particle collisions at the energy frontier can probe the nature of invisible dark matter via production in association with recoiling visible objects. We propose a new potential production mode, in which dark matter is produced by the decay of a heavy dark Higgs boson radiated from a heavy $W'$ boson. In such a model, motivated by left-right symmetric theories, dark matter would not be pair produced in association with other recoiling objects due to its lack of direct coupling to quarks or gluons. We study the hadronic decay mode via $W'\rightarrow tb$ and estimate the LHC exclusion sensitivity at 95\% confidence level to be $10^2-10^5$ fb for $W'$ boson masses between 250 and 1750 GeV.

hep-ph↗

arXiv2024

Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks

Reconstructing unstable heavy particles requires sophisticated techniques to sift through the large number of possible permutations for assignment of detector objects to the underlying partons. Anapproach based on a generalized attention mechanism, symmetry preserving attention networks (SPA-NET), has been previously applied to top quark pair decays at the Large Hadron Collider which produce only hadronic jets. Here we extend the SPA-NET architecture to consider multiple input object types, such as leptons, as well as global event features, such as the missing transverse momentum. Inaddition, we provide regression and classification outputs to supplement the parton assignment. We explore the performance of the extended capability of SPA-NET in the context of semi-leptonic decays of top quark pairs as well as top quark pairs produced in association with a Higgs boson. We find significant improvements in the power of three representative studies: a search for ttH, a measurement of the top quark mass, and a search for a heavy Z' decaying to top quark pairs. We present ablation studies to provide insight on what the network has learned in each case.

hep-ex↗

arXiv2024

The Landscape of Unfolding with Machine Learning

Recent innovations from machine learning allow for data unfolding, without binning and including correlations across many dimensions. We describe a set of known, upgraded, and new methods for ML-based unfolding. The performance of these approaches are evaluated on the same two datasets. We find that all techniques are capable of accurately reproducing the particle-level spectra across complex observables. Given that these approaches are conceptually diverse, they offer an exciting toolkit for a new class of measurements that can probe the Standard Model with an unprecedented level of detail and may enable sensitivity to new phenomena.

hep-ph↗