ML4Jets2023

Session

Reconstruction & Representation Learning

6 Nov 2023, 16:00

Main Auditorium (DESY)

Conveners

Reconstruction & Representation Learning

• Peter Loch (University of Arizona (US))

Presentation materials

Zoom link

71. Generic representations of jets at detector-level with self supervised learning

Etienne Dreyer (Weizmann Institute of Science (IL))

06/11/2023, 16:00

Supervised learning has been used successfully for jet classification and to predict a range of jet properties, such as mass and energy. Each model learns to encode jet features, resulting in a representation that is tailored to its specific task. But could the common elements underlying such tasks be combined in a single model trained to extract features generically? To address this question,...

107. CoCo: Contrastive Combinatorics

Debajyoti Sengupta (Universite de Geneve (CH))

06/11/2023, 16:15

We present CoCo (Contrastive Combinatorics) a new approach using contrastive learning to solve object assignment in HEP. By utilizing contrastive objectives, CoCo aims to pull jets originating from the same parent closer together in an embedding space while pushing unrelated jets apart.
This approach can be extended natively to have multiple objectives for each subsequent particle in a decay...

122. Identifying semi-visible jets with darkCLR

Tanmoy Modak

06/11/2023, 16:30

Abstract: Unsupervised machine learning enables us to utilize all available information within a jet to identify anomalies. Nevertheless, the network's need to acquire knowledge about the inherent symmetries within the raw data structure can hinder this process. Self-supervised contrastive learning representation offers a novel approach that preserves physical symmetries in the data while...

62. Reconstructing full pp collision events with HGPflow

Nilotpal Kakati (Weizmann Institute of Science (IL))

06/11/2023, 16:45

Last year we proposed a novel hypergraph-based algorithm (HGPflow) for one-shot prediction of particle cardinality, class, and kinematics in a dataset of single jets. This approach has the advantage of introducing energy conservation as an inductive bias, promoting both interpretability and performance gains at the particle and jet levels. We now deploy an upgraded version of HGPflow to the...

89. Scalable neural network models and terascale datasets for particle-flow reconstruction

Joosep Pata (National Institute of Chemical Physics and Biophysics (EE))

06/11/2023, 17:30

We study scalable machine learning models for full event reconstruction in high-energy electron-positron collisions based on a highly granular detector simulation. Particle-flow (PF) reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters or hits. We compare a graph neural network and kernel-based transformer and demonstrate that both avoid...

23. Masked particle modelling

Mr Matthew Leigh (University of Geneva)

06/11/2023, 17:45

The Bert pretraining paradigm has proven to be highly effective in many domains including natural language processing, image processing and biology. To apply the Bert paradigm the data needs to be described as a set of tokens, and each token needs to be labelled. To date the Bert paradigm has not been explored in the context of HEP. The samples that form the data used in HEP can be described...

126. ML-assisted reconstruction of hadron-collider events with mini-jets

Josef Modestus Murnauer (Max Planck Society (DE))

06/11/2023, 18:00

The reconstruction of physical observables in hadron collider events from recorded experimental quantities poses a repeated task in almost any data analysis at the LHC. While the experiments record hits in tracking detectors and signals in the calorimeters, which are subsequently combined into particle-flow objects, jets, muons, electrons, missing transverse energy, or similar high-level...