arXiv subjects

Wasikul Islam

Publications and source records attributed to Wasikul Islam.

5 recordsLinked to original sources

arXiv2026

Compact Representation of Particle-Collision Events for Physics-Informed Machine Learning

We introduce a compact, physics-driven event representation, RMM-C46, designed to compress the high-dimensional rapidity mass matrix (RMM) into a low-dimensional, interpretable feature set suitable for physics-informed machine learning (ML) and quantum computing applications. The full RMM encodes detailed pairwise correlations among jets, b-jets, leptons, photons, and missing transverse energy but contains more than a thousand values per event, making it computationally heavy for large-scale training and incompatible with current low-qubit quantum devices. The proposed RMM-C46 input space for ML preserves the physical block structure of the RMM through aggregated invariant mass, rapidity difference, and transverse energy components, reducing the size of the original RMM by over an order of magnitude while maintaining interpretability. Applied to simulated proton-proton collisions at centre-of-mass energy of 13.6 TeV, these representations match or exceed the discriminative performance of the full RMM in both supervised and unsupervised ML tasks. Their compactness, stability, and physics transparency also make them naturally compatible with near-term quantum machine learning architectures. RMM-C46 provides a scalable, efficient, and quantum-ready alternative to the full RMM for next-generation collider physics analyses.

hep-ph↗

arXiv2025

New Physics Searches at the LHC through Event-based Anomaly Detection and Development of ADFilter Web-tool

This work presents advancements in model-agnostic searches for new physics at the Large Hadron Collider (LHC) through the application of event-based anomaly detection techniques utilizing unsupervised machine learning. We discuss the advantages of the anomaly detection approach, as demonstrated in a recent ATLAS analysis, and introduce ADFilter, a web-based tool designed to process collision events using autoencoders based on deep unsupervised neural networks. ADFilter calculates loss distributions for input events, aiding in determining the degree to which events can be considered anomalous. Real-life examples are provided to demonstrate how the tool can be used to reinterpret existing LHC results, with the goal of significantly improving exclusion limits. Furthermore, we present a comparative study between anomaly detection and supervised machine learning techniques, using the search for heavy resonances decaying into two or more Higgs bosons as a representative case to demonstrate the application and effectiveness of these methods.

hep-ph↗

arXiv2025

WIPUNet: A Physics-inspired Network with Weighted Inductive Biases for Image Denoising

In high-energy particle physics, collider measurements are contaminated by "pileup", overlapping soft interactions that obscure the hard-scatter signal of interest. Dedicated subtraction strategies exploit physical priors such as conservation, locality, and isolation. Inspired by this analogy, we investigate how such principles can inform image denoising by embedding physics-guided inductive biases into neural architectures. This paper is a proof of concept: rather than targeting state-of-the-art (SOTA) benchmarks, we ask whether physics-inspired priors improve robustness under strong corruption. We introduce a hierarchy of PU-inspired denoisers: a residual CNN with conservation constraints, its Gaussian-noise variants, and the Weighted Inductive Pileup-physics-inspired U-Network for Denoising (WIPUNet), which integrates these ideas into a UNet backbone. On CIFAR-10 with Gaussian noise at $\sigma\in\{15,25,50,75,100\}$, PU-inspired CNNs are competitive with standard baselines, while WIPUNet shows a \emph{widening margin} at higher noise. Complementary BSD500 experiments show the same trend, suggesting physics-inspired priors provide stability where purely data-driven models degrade. Our contributions are: (i) translating pileup-mitigation principles into modular inductive biases; (ii) integrating them into UNet; and (iii) demonstrating robustness gains at high noise without relying on heavy SOTA machinery.

cs.CV↗

arXiv2025

Enhancing Sensitivity for Di-Higgs Boson Searches Using Anomaly Detection and Supervised Machine Learning Techniques

This paper explores different strategies for enhancing sensitivity to new heavy resonances that decay into two or more Higgs bosons. This is achieved using two neural network architectures: an unsupervised autoencoder for anomaly detection and a supervised classifier. The autoencoder is trained on a small fraction of Standard Model (SM) Monte Carlo simulated events to calculate the loss distribution for input events, aiding in determining the extent to which events can be considered anomalous. The supervised classifier uses the same inputs but is trained on events simulated using both beyond Standard Model (BSM) and SM processes. By applying selection cuts to the output scores, we compare the sensitivities of the two approaches.

hep-ph↗

arXiv2024

ADFilter -- A Web Tool for New Physics Searches With Autoencoder-Based Anomaly Detection Using Deep Unsupervised Neural Networks

A web-based tool called ADFilter was developed to process collision events using autoencoders based on a deep unsupervised neural network. The autoencoders are trained on a small fraction of either collision data or Standard Model Monte Carlo simulations. The tool calculates loss distributions for input events, helping to determine the degree to which the events can be considered anomalous. It also calculates two-body invariant masses both before and after the autoencoders, as well as cross sections. Real-life examples are provided to demonstrate how the tool can be used to reinterpret existing LHC results with the goal of significantly improving exclusion limits.

hep-ph↗