Related papers: Soft Classification of Diffractive Interactions at…

Classification models may often suffer from "structure imbalance" between training and testing data that may occur due to the deficient data collection process. This imbalance can be represented by the learning using privileged information…

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…

Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where…

Existing data on total cross sections, on elastic scattering at small, moderate and large values of $t$, and on diffraction dissociation, reveal a surprisingly simple phenomenology, but they throw up many questions for the LHC to answer.

We present a new framework for modeling hard diffractive events in photoproduction, implemented in the general purpose event generator Pythia 8. The model is an extension of the model for hard diffraction with dynamical gap survival in pp…

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…

In this talk, the recent data on diffractive electron-proton interactions at HERA are reviewed. The question of diffraction as a soft or hard process is addressed and discussed in the context of inclusive diffraction, vector meson…

In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments. Robots must analyze interactions with objects to ensure safety and facilitate meaningful workflows. One critical aspect is…

Results from the large hadron collider (LHC) show that no available Monte Carlo simulation incorporates our pre-LHC knowledge of soft and hard diffraction in a way that could be reliably extrapolated to LHC energies. As a simulation is…

Deep learning techniques are currently being investigated for high energy physics experiments, to tackle a wide range of problems, with quark and gluon discrimination becoming a benchmark for new algorithms. One weakness is the traditional…

Understanding the modification of jets and high-$p_T$ probes in small systems requires the integration of soft and hard physics. We present recent developments in extending the JETSCAPE framework to build an event generator, which includes…

Phasor measurement units (PMUs) are being widely installed on power systems, providing a unique opportunity to enhance wide-area situational awareness. One essential application is the use of PMU data for real-time event identification.…

We apply the Linked Dipole Chain model to hadronic collisions using a modified version of the LDCMC Monte Carlo program. In particular we investigate the effects of multiple scatterings, which in this framework are reformulated in terms of…

We make a brief presentation of the soft colour interactions models, the Soft Colour Interaction and the Generalised Area Law, and summarise the results when they are applied to p-pbar scattering. The models give a good description of the…

We calculate the probability of large rapidity gaps in high energy hadronic collisions using a model based on QCD mini-jets and soft gluon emission down into the infrared region. Comparing with other models we find a remarkable agreement…

Modern machine learning forces practitioners to choose between powerful but expensive deep networks and fast but limited classical algorithms. Here we introduce Soft Learning, a framework that maintains a library of heterogeneous…

We study the benefit of modern simulation-based inference to constrain particle interactions at the LHC. We explore ways to incorporate known physics structures into likelihood estimation, specifically morphing-aware estimation and…

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…

Multivariate Hawkes Processes (MHPs) are an important class of temporal point processes that have enabled key advances in understanding and predicting social information systems. However, due to their complex modeling of temporal…

Diffusion-based classifiers such as those relying on the Personalized PageRank and the Heat kernel, enjoy remarkable classification accuracy at modest computational requirements. Their performance however is affected by the extent to which…