115 citations · 331 across the 18 of their papers we have counts for
18 papers
Equivalence of maximal and generic reachability for non-universal Variational Quantum Circuits
Vishal S. Ngairangbam, Michael Spannowsky
Employing problem-specific non-universal Variational Quantum Circuits aligned with a suitable state preparation has become a standard approach to counter the difficulty in training…
From Reachability to Learnability: Geometric Design Principles for Quantum Neural Networks
Vishal S. Ngairangbam, Michael Spannowsky
Classical deep networks are effective because depth enables adaptive geometric deformation of data representations. In quantum neural networks (QNNs), however, depth or state reach…
Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
Partha Konar, Vishal S. Ngairangbam, Michael Spannowsky +1
Deep learning has achieved remarkable success in jet classification tasks, yet a key challenge remains: understanding what these models learn and how their features relate to known…
Improved Ground State Estimation in Quantum Field Theories via Normalising Flow-Assisted Neural Quantum States
Vishal S. Ngairangbam, Michael Spannowsky, Timur Sypchenko
We propose a hybrid variational framework that enhances Neural Quantum States (NQS) with a Normalising Flow-based sampler to improve the expressivity and trainability of quantum ma…
Enhancing anomaly detection with topology-aware autoencoders
Vishal S. Ngairangbam, Błażej Rozwoda, Kazuki Sakurai +1
Anomaly detection in high-energy physics is essential for identifying new physics beyond the Standard Model. Autoencoders provide a signal-agnostic approach but are limited by the…
Optimal Equivariant Architectures from the Symmetries of Matrix-Element Likelihoods
Daniel Maître, Vishal S. Ngairangbam, Michael Spannowsky
The Matrix-Element Method (MEM) has long been a cornerstone of data analysis in high-energy physics. It leverages theoretical knowledge of parton-level processes and symmetries to…
Optimal Symmetries in Binary Classification
Vishal S. Ngairangbam, Michael Spannowsky
We develop a theoretical foundation for designing group-equivariant neural networks that align the choice of symmetries with the underlying probability distributions of the data. U…
Foundations of automatic feature extraction at LHC--point clouds and graphs
Akanksha Bhardwaj, Partha Konar, Vishal S. Ngairangbam
Deep learning algorithms will play a key role in the upcoming runs of the Large Hadron Collider (LHC), helping bolster various fronts ranging from fast and accurate detector simula…
Equivariant, Safe and Sensitive -- Graph Networks for New Physics
Akanksha Bhardwaj, Christoph Englert, Wrishik Naskar +2
This study introduces a novel Graph Neural Network (GNN) architecture that leverages infrared and collinear (IRC) safety and equivariance to enhance the analysis of collider data f…
Interpretable deep learning models for the inference and classification of LHC data
Vishal S. Ngairangbam, Michael Spannowsky
The Shower Deconstruction methodology is pivotal in distinguishing signal and background jets, leveraging the detailed information from perturbative parton showers. Rooted in the N…
Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
Partha Konar, Vishal S. Ngairangbam, Michael Spannowsky
In this study, we critically evaluate the approximation capabilities of existing infra-red and collinear (IRC) safe feature extraction algorithms, namely Energy Flow Networks (EFNs…
LLPNet: Graph Autoencoder for Triggering Light Long-Lived Particles at HL-LHC
Biplob Bhattacherjee, Partha Konar, Vishal Singh Ngairangbam +1
In the search for exotic events involving displaced particles at HL-LHC, the triggering at the level-1 (L1) system will pose a significant challenge. This is particularly relevant…
IRC-safe Graph Autoencoder for unsupervised anomaly detection
Oliver Atkinson, Akanksha Bhardwaj, Christoph Englert +3
Anomaly detection through employing machine learning techniques has emerged as a novel powerful tool in the search for new physics beyond the Standard Model. Historically similar t…
Influence of QCD parton shower in deep learning invisible Higgs through vector boson fusion
Partha Konar, Vishal S. Ngairangbam
Vector boson fusion established itself as a highly reliable channel to probe the Higgs boson and an avenue to uncover new physics at the Large Hadron Collider. This channel provide…
Anomaly detection in high-energy physics using a quantum autoencoder
Vishal S. Ngairangbam, Michael Spannowsky, Michihisa Takeuchi
The lack of evidence for new interactions and particles at the Large Hadron Collider has motivated the high-energy physics community to explore model-agnostic data-analysis approac…
Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
Partha Konar, Vishal S. Ngairangbam, Michael Spannowsky
Hadronic signals of new-physics origin at the Large Hadron Collider can remain hidden within the copiously produced hadronic jets. Unveiling such signatures require highly performa…
Anomaly detection with Convolutional Graph Neural Networks
Oliver Atkinson, Akanksha Bhardwaj, Christoph Englert +2
We devise an autoencoder based strategy to facilitate anomaly detection for boosted jets, employing Graph Neural Networks (GNNs) to do so. To overcome known limitations of GNN auto…
Invisible Higgs search through Vector Boson Fusion: A deep learning approach
Vishal S. Ngairangbam, Akanksha Bhardwaj, Partha Konar +1
Vector boson fusion proposed initially as an alternative channel for finding heavy Higgs has now established itself as a crucial search scheme to probe different properties of the…