New method identifies quark and gluon jets from collider data.
problem Determine quark and gluon jet distributions from collider data.
method Apply topic modeling to jet distributions, using parton shower and theoretical predictions.
result Determined separate quark and gluon jet distributions and spectra.
Recursive neural networks improve quark/gluon tagging performance.
problem Improving quark/gluon tagging accuracy using machine learning.
method Recursive neural networks (RecNNs) that embed jet clustering history recursively.
result RecNNs outperform traditional boosted decision tree (BDT) by a few percent in gluon rejection rate.
A new jet constituent-based method for top quark tagging achieves high background rejection.
problem Tagging highly energetic jets resulting from top quark decays.
method Sequential approach using ordered jet constituents as inputs, avoiding loss of information.
result Achieves a background rejection of 45 at a 50% efficiency operating point.
Deep learning improves jet discrimination in particle physics.
problem Automating quark/gluon jet discrimination in collider physics.
method Convolutional neural networks trained on color-enhanced jet images.
result Deep networks outperform traditional jet variables in discrimination.
Iterative subtraction method outperforms other feature ranking techniques in high-energy physics.
problem Determining the most important features for classification in high-energy physics experiments.
method Comparison of feature ranking methods including Iterative Addition, Iterative Removal, and BDT Selection Frequency.
result Iterative Removal method is the most efficient for feature ranking in classification tasks.
We demonstrate the agreement between the Higgs branches of two N=2 theories proposed by Argyres and Seiberg to be S-dual, namely the SU(3) gauge theory with six quarks, and the SU(2) gauge theory with one pair of quarks coupled to the superconformal theory with E_6 flavor symmetry. In mathematical terms, we demonstrate…
DeepJet improves jet flavor classification and quark-gluon tagging.
problem Jet flavor classification in high-energy physics experiments.
method Proposes a novel deep learning architecture, DeepJet, for improved performance.
result Improves heavy flavor classification performance and extends to quark-gluon tagging.
Paper tackles classification without labels using statistical mixtures in collider physics.
problem Training models on imperfect simulations in high energy physics.
method Classification without labels (CWoLa) paradigm, distinguishing statistical mixtures of classes.
result Optimal classifier in CWoLa is also optimal in fully-supervised case.
Geometric QCD framework establishes stable vacuum for quark confinement.
problem Quark confinement in QCD.
method Geometric construction of stable vacuum using Hodge-dual surfaces.
result Existence and stability of the Hodge-dual surface in 4D ensures quark confinement.
Equivariant neural network simplifies particle physics models.
problem Complexity and interpretability in particle physics classification.
method Lorentz group equivariant neural network architecture.
result Simplified, interpretable models with fewer parameters.
New model improves QGP simulation efficiency and accuracy.
problem Limited QGP simulation runs due to high computational cost.
method Additive Multi-Index Gaussian process (AdMIn-GP) model.
result Significantly improved surrogate modeling performance.
New method improves machine learning in physics.
problem Improving machine learning performance in physics with limited data.
method Weakly supervised classification using class proportions as input.
result Weakly supervised classification matches fully supervised algorithms in quark vs gluon tagging.
Develops neural networks for reductive Lie groups, enhancing symmetry respect.
problem Symmetry respect in neural networks for reductive Lie groups.
method General equivariant neural network architecture for any reductive Lie Group G.
result Demonstrates generality and performance in top quark decay tagging and shape recognition.
Compactification of AdS5 allows studying meson behavior in QCD.
problem Understanding meson behavior in Quantum Chromodynamics (QCD).
method Deforming AdS5 metric to model Coulomb interaction between charges.
result Proposed conformal deformation provides a quantum mechanical description of mesons.
MLPF uses graph neural networks to improve particle-flow reconstruction in high-pileup conditions.
problem Improving particle-flow reconstruction in high-pileup conditions at high-luminosity LHC.
method End-to-end trainable machine-learned particle-flow algorithm based on graph neural networks.
result MLPF improves physics response and demonstrates scalable reconstruction in high-pileup environments.
A new transform links rotating calorons to solutions of a differential equation.
problem Existence and characterization of rotating calorons.
method Formulated a Nahm transform to relate rotating calorons to solutions of a delayed-differential equation.
result Existence of an eight-parameter family of rotating calorons with nontrivial holonomy.
This paper identifies braided 3-belts that can be written in a braid-only form.
problem Identifying braided 3-belts that can be written in a braid-only form.
method Developed an algorithm to calculate the braid word for braided 3-belts and determined the conditions for knotted boundaries.
result Identified the set of braided 3-belts that can be written in a braid-only form and derived a formula for the Jones polynomial for knotted boundaries.
We propose a construction of Kähler and non-Kähler Calabi-Yau manifolds by branched double covers of twistor spaces. In this construction we use the twistor spaces of four-manifolds with self-dual conformal structures, with the examples of connected sum of n P2s. We also construct K3-fibered Calabi-Ya…
This paper tackles class imbalance in high energy physics experiments.
problem Extracting a signal from a large background in high energy physics experiments.
method Overview of class imbalance techniques and case studies.
result Demonstrates the effectiveness of class imbalance techniques in high energy physics experiments.
New method uses neural networks to estimate parameters without needing detector simulations.
problem Estimating parameters in high-energy physics with detector effects.
method Two-level fitting approach: SRGN (Simulation-level fit based on Reweighting Generator-level events with Neural networks).
result Demonstrated using simulated datasets, SRGN can estimate parameters without detector effects.
LSTM networks improve top jet tagging at the LHC.
problem Boosted top quark tagging at the LHC.
method Incorporating Long Short-Term Memory (LSTM) networks into jet constituent analysis.
result Best LSTM network achieves 100 background rejection at 50% signal efficiency.
Machine learning improves jet charge classification.
problem Classifying jets according to their electric charge.
method Convolutional, recurrent, and recursive neural networks, including distance within the jet and clustering history.
result Significant improvement in jet charge extraction over traditional methods.
Moment Pooling reduces latent space dimensions in machine learning models.
problem High-dimensional latent spaces in machine learning models are hard to interpret.
method Moment Pooling extends Deep Sets networks to arbitrary multivariate moments.
result Latent dimensions as small as 1 can achieve similar performance to higher dimensions.
A method smears likelihood to reveal physical energy scales in jet identification.
problem Interpretability of machine learning in particle physics.
method Smearing or averaging over events within a metric energy distance.
result Discrimination power increases as resolution decreases, showing sensitivity to all energy scales.
Investigates the fundamental components of attention mechanisms.
problem Understanding the building blocks of attention in deep learning.
method Classified and studied three key mechanisms: additive, multiplicative output, and synaptic attention.
result Additive activation attention is central in proofs of lower bounds.
Improved jet tagging reduces systematic uncertainties and enhances signal purity.
problem Boosted resonance decay signals from jets are difficult to distinguish from background.
method Adversarial neural networks to decorrelate jet substructure tagger.
result Adversarial trained tagger outperforms conventional methods in discovery significance.
Tensor networks improve b-jet classification in high-energy physics.
problem Classifying jets from b-quarks in proton-proton collisions.
method Quantum-inspired machine learning using tensor networks.
result Optimized classification of b-jets with improved precision and speed.
Unified access package for fundamental physics datasets simplifies machine learning.
problem Lack of unified access to datasets from multiple fundamental physics disciplines.
method Unified Python package with common interface and reference models.
result Graph-based neural networks perform similarly to dedicated methods on various datasets.
We study the differential geometry of principal G-bundles whose base space is the space of free paths (loops) on a manifold M. In particular we consider connections defined in terms of pairs (A,B), where A is a connection for a fixed principal bundle P(M,G) and B is a 2-form on M. The relevant curvatures, parallel tran…
Deep Sets improve jet discrimination in particle physics.
problem Representing and learning from collider events with variable-length particle sets.
method Energy Flow Networks and Particle Flow Networks, based on Deep Sets framework.
result Improved or similar performance in discriminating quark jets from gluon jets compared to existing methods.
Study of M-theory dual of thermal QCD-like theories at intermediate coupling.
problem Missing top-down holographic dual for thermal QCD-like theories at intermediate 't Hooft coupling.
method Analysis of O(R4) corrections and O(lp6) corrections in the MQGP background. result Discovery of O(R4) corrections and G-structure classification of underlying geometries.