Steven Tsan

University of California, San Diego

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

J. Duarte

University of California, San Diego

M. Pierini

European Organization for Nuclear Research

J. Ngadiuba

Fermi National Accelerator Laboratory

R. Kansal

University of California, San Diego

Pratik Jawahar

University of Manchester

T. K. Aarrestad

ETH Zurich

D. Díaz

University of California, San Diego

Anders Andreassen

Google (United States)

Kees Benkendorfer

Harvard University Press

Anthony Aportela

University of California System

Cooperative Institutions

A. Alikhanyan National Laboratory

Fermi National Accelerator Laboratory

European Organization for Nuclear Research

Institute of High Energy Physics

University of Adelaide

University of Antwerp

Massachusetts Institute of Technology

Lawrence Berkeley National Laboratory

University of Chicago

Atlas Scientific (United States)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows

arXiv (Cornell University) (2021)

Pratik Jawahar T. K. Aarrestad N. Chernyavskaya M. Pierini Kinga Anna Woźniak

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.

Autoencoder

Anomaly (physics)

Benchmark (surveying)

10.48550/arxiv.2110.08508

Cite

Citations (0)

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

Frontiers in Big Data (2022)

Pratik Jawahar T. K. Aarrestad N. Chernyavskaya M. Pierini Kinga A. Wozniak

Autoencoder

Anomaly (physics)

Benchmark (surveying)

10.3389/fdata.2022.803685

Cite

Citations (35)

Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance

arXiv (Cornell University) (2021)

Steven Tsan R. Kansal Anthony Aportela D. Díaz J. Duarte

Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of particles produced in collisions such as those at the CERN Large Hadron Collider. We explore the use of graph-based autoencoders, which operate on jets in their "particle cloud" representations and can leverage the interdependencies among the particles within a jet, for such tasks. Additionally, we develop a differentiable approximation to the energy mover's distance via a graph neural network, which may subsequently be used as a reconstruction loss function for autoencoders.

Leverage (statistics)

10.48550/arxiv.2111.12849

Cite

Citations (12)

The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics

arXiv (Cornell University) (2021)

Gregor Kasieczka Benjamin Nachman David Shih O. Amram Anders Andreassen

A new paradigm for data-driven, model-agnostic new physics searches at colliders is emerging, and aims to leverage recent breakthroughs in anomaly detection and machine learning. In order to develop and benchmark new anomaly detection methods within this framework, it is essential to have standard datasets. To this end, we have created the LHC Olympics 2020, a community challenge accompanied by a set of simulated collider events. Participants in these Olympics have developed their methods using an R&D dataset and then tested them on black boxes: datasets with an unknown anomaly (or not). This paper will review the LHC Olympics 2020 challenge, including an overview of the competition, a description of methods deployed in the competition, lessons learned from the experience, and implications for data analyses with future datasets as well as future colliders.

Leverage (statistics)

Benchmark (surveying)

Anomaly (physics)

Source

Cite

Citations (34)

Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance

arXiv (Cornell University) (2021)

Steven Tsan R. Kansal Anthony Aportela D. Díaz J. Duarte

Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of particles produced in collisions such as those at the CERN Large Hadron Collider. We explore the use of graph-based autoencoders, which operate on jets in their particle cloud representations and can leverage the interdependencies among the particles within a jet, for such tasks. Additionally, we develop a differentiable approximation to the energy mover's distance via a graph neural network, which may subsequently be used as a reconstruction loss function for autoencoders.

Leverage (statistics)

Source

Cite

Citations (0)

Induced Generative Adversarial Particle Transformers

arXiv (Cornell University) (2023)

Anni Li Venkat Krishnamohan R. Kansal Rounak Sen Steven Tsan

In high energy physics (HEP), machine learning methods have emerged as an effective way to accurately simulate particle collisions at the Large Hadron Collider (LHC). The message-passing generative adversarial network (MPGAN) was the first model to simulate collisions as point, or ``particle'', clouds, with state-of-the-art results, but suffered from quadratic time complexity. Recently, generative adversarial particle transformers (GAPTs) were introduced to address this drawback; however, results did not surpass MPGAN. We introduce induced GAPT (iGAPT) which, by integrating ``induced particle-attention blocks'' and conditioning on global jet attributes, not only offers linear time complexity but is also able to capture intricate jet substructure, surpassing MPGAN in many metrics. Our experiments demonstrate the potential of iGAPT to simulate complex HEP data accurately and efficiently.

Substructure

10.48550/arxiv.2312.04757

Cite

Citations (1)

Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning

HAL (Le Centre pour la Communication Scientifique Directe) (2022)

Phiala E. Shanahan K. Terao Daniel Whiteson Gert Aarts Andreas Adelmann

Frontier

Source

Cite

Citations (6)

arXiv : Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows