Elsa: enhanced latent spaces for improved collider simulations
Abstract Simulations play a key role for inference in collider physics. We explore various approaches for enhancing the precision of simulations using machine learning, including interventions at the end of the simulation chain (reweighting), at the beginning of the simulation chain (pre-processing)...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-09-01
|
| Series: | European Physical Journal C: Particles and Fields |
| Online Access: | https://doi.org/10.1140/epjc/s10052-023-11989-8 |
| _version_ | 1797647227021164544 |
|---|---|
| author | Benjamin Nachman Ramon Winterhalder |
| author_facet | Benjamin Nachman Ramon Winterhalder |
| author_sort | Benjamin Nachman |
| collection | DOAJ |
| description | Abstract Simulations play a key role for inference in collider physics. We explore various approaches for enhancing the precision of simulations using machine learning, including interventions at the end of the simulation chain (reweighting), at the beginning of the simulation chain (pre-processing), and connections between the end and beginning (latent space refinement). To clearly illustrate our approaches, we use W + jets matrix element surrogate simulations based on normalizing flows as a prototypical example. First, weights in the data space are derived using machine learning classifiers. Then, we pull back the data-space weights to the latent space to produce unweighted examples and employ the Latent Space Refinement (Laser) protocol using Hamiltonian Monte Carlo. An alternative approach is an augmented normalizing flow, which allows for different dimensions in the latent and target spaces. These methods are studied for various pre-processing strategies, including a new and general method for massive particles at hadron colliders that is a tweak on the widely-used RamboOnDiet mapping. We find that modified simulations can achieve sub-percent precision across a wide range of phase space. |
| first_indexed | 2024-03-11T15:14:17Z |
| format | Article |
| id | doaj.art-e6961ae52ba34a1d9716a9c12fecc66d |
| institution | Directory Open Access Journal |
| issn | 1434-6052 |
| language | English |
| last_indexed | 2024-03-11T15:14:17Z |
| publishDate | 2023-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Physical Journal C: Particles and Fields |
| spelling | doaj.art-e6961ae52ba34a1d9716a9c12fecc66d2023-10-29T12:33:53ZengSpringerOpenEuropean Physical Journal C: Particles and Fields1434-60522023-09-0183911610.1140/epjc/s10052-023-11989-8Elsa: enhanced latent spaces for improved collider simulationsBenjamin Nachman0Ramon Winterhalder1Physics Division, Lawrence Berkeley National LaboratoryCP3, Université Catholique de LouvainAbstract Simulations play a key role for inference in collider physics. We explore various approaches for enhancing the precision of simulations using machine learning, including interventions at the end of the simulation chain (reweighting), at the beginning of the simulation chain (pre-processing), and connections between the end and beginning (latent space refinement). To clearly illustrate our approaches, we use W + jets matrix element surrogate simulations based on normalizing flows as a prototypical example. First, weights in the data space are derived using machine learning classifiers. Then, we pull back the data-space weights to the latent space to produce unweighted examples and employ the Latent Space Refinement (Laser) protocol using Hamiltonian Monte Carlo. An alternative approach is an augmented normalizing flow, which allows for different dimensions in the latent and target spaces. These methods are studied for various pre-processing strategies, including a new and general method for massive particles at hadron colliders that is a tweak on the widely-used RamboOnDiet mapping. We find that modified simulations can achieve sub-percent precision across a wide range of phase space.https://doi.org/10.1140/epjc/s10052-023-11989-8 |
| spellingShingle | Benjamin Nachman Ramon Winterhalder Elsa: enhanced latent spaces for improved collider simulations European Physical Journal C: Particles and Fields |
| title | Elsa: enhanced latent spaces for improved collider simulations |
| title_full | Elsa: enhanced latent spaces for improved collider simulations |
| title_fullStr | Elsa: enhanced latent spaces for improved collider simulations |
| title_full_unstemmed | Elsa: enhanced latent spaces for improved collider simulations |
| title_short | Elsa: enhanced latent spaces for improved collider simulations |
| title_sort | elsa enhanced latent spaces for improved collider simulations |
| url | https://doi.org/10.1140/epjc/s10052-023-11989-8 |
| work_keys_str_mv | AT benjaminnachman elsaenhancedlatentspacesforimprovedcollidersimulations AT ramonwinterhalder elsaenhancedlatentspacesforimprovedcollidersimulations |