arXiv subjects

Tae Min Hong

Publications and source records attributed to Tae Min Hong.

11 recordsLinked to original sources

arXiv2026

Chopping and distilling variational autoencoders for real-time anomaly detection in high energy physics

Anomaly detection (AD) has recently emerged as an exciting alternative to conventional search strategies in high energy physics using artificial intelligence (AI) and machine learning (ML). The integration of these techniques into trigger systems is even more recent, but represents a crucial step in expanding the coverage of LHC triggers. In this paper, we explore the direct comparison, as well as combination, of two compression techniques for variational autoencoder (VAE) AD trigger algorithms: utilizing only latent-space derived variables and therefore requiring only half of the VAE that we call "chopping" and applying knowledge distillation (KD) to distill the VAE into a student architecture that we call "distillation." We demonstrate the feasibility of deploying such techniques on an FPGA within the resource and latency constraints of an LHC trigger environment and further find that a combination of the two leads to the smallest models that maintain, and in some cases, improve, performance with respect to the original VAE architecture.

physics.ins-det↗

arXiv2026

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML), silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science.

physics.ins-det↗

arXiv2026

Memristive tabular variational autoencoder for compression of analog data in high energy physics

We present an implementation of edge AI to compress data on an in-memory analog content-addressable memory (ACAM) device. A variational autoencoder is trained on a simulated sample of energy measurements from incident high-energy electrons on a generic three-layer scintillator-based calorimeter. The encoding part is distilled into tabular format by regressing the latent space variables using decision trees, which is then programmed on a memristor-based ACAM. In real-time, the ACAM compresses 48 continuously valued incoming energies measured by the calorimeter sensors into the latent space, achieving a compression factor of 12x, which is transmitted off-detector for decompression. The performance result of the ACAM, obtained using the Structural Simulation Toolkit, the SST open source framework, gives a latency value of 24 ns and a throughput of 330M compressions per second, i.e., 3 ns between successive inputs, and an average energy consumption of 4.1 nJ per compression.

physics.ins-det↗

arXiv2025

Ring-based ML calibration with in situ pileup correction for real-time jet triggers

We present a machine learning (ML) method to calibrate hadronic jet energy in real-time trigger systems of the High-Luminosity Large Hadron Collider (HL-LHC) using an efficient implementation on field programmable gate arrays (FPGA). Regression is done to estimate the transverse energy of jet candidates, using concentric rings of electromagnetic and hadronic contributions in 0.1 x 0.1 towers around fixed-radius cone jet seeds, that accounts for in situ pileup correction. Classification separates hard-scatter jets from those due to pileup using the same inputs; its output provides a correction for the regression estimate. The algorithm is tested on simulated samples using an ATLAS-inspired detector in the dense environment of 200 simultaneous proton-proton collisions per bunch crossing. Our method improves the signal efficiency of saving Higgs pair production in HH -> bbbb by a factor of two over the traditional cone jet algorithm in real-time trigger systems.

hep-ph↗

arXiv2024

Nanosecond hardware regression trees in FPGA at the LHC

We present a generic parallel implementation of the decision tree-based machine learning (ML) method in hardware description language (HDL) on field programmable gate arrays (FPGA). A regression problem in high energy physics at the Large Hadron Collider is considered: the estimation of the magnitude of missing transverse momentum using boosted decision trees (BDT). A forest of twenty decision trees each with a maximum depth of ten using eight input variables of 16-bit precision is executed with a latency of less than 10 ns using O(0.1%) resources on Xilinx UltraScale+ VU9P -- approximately ten times faster and five times smaller compared to similar designs using high level synthesis (HLS) -- without the use of digital signal processors (DSP) while eliminating the use of block RAM (BRAM). We also demonstrate a potential application in the estimation of muon momentum for ATLAS RPC at HL-LHC.

hep-ex↗

arXiv2024

Illuminating all-hadronic final states with a photon: Exotic decays of the Higgs boson to four bottom quarks in vector boson fusion plus gamma at hadron colliders

We investigate the potential to detect Higgs boson decays to four bottom quarks through a pair of pseudoscalars, a final state that is predicted by many theories beyond the Standard Model. For the first time, the signal sensitivity is evaluated for the final state using the vector boson fusion (VBF) production with and without an associated photon, for the Higgs at $m_H=125\,\textrm{GeV}$, at hadron colliders. The signal significance is $4$ to $6σ$, depending on the pseudoscalar mass $m_a$, when setting the the Higgs decay branching ratio to unity, using an integrated luminosity of $150\,\textrm{fb}^{-1}$ at $\sqrt{s}=13\,\textrm{TeV}$. This corresponds to an upper limit of $0.3$, on the Higgs branching ratio to four bottom quarks, with a non-observation of the decay. We also consider several variations of selection requirements - input variables for the VBF tagging and the kinematic variables for the photon - that could help guide the design of new triggers for the Run-3 period of the LHC and for the HL-LHC.

hep-ph↗

arXiv2024

Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays

We present an interpretable implementation of the autoencoding algorithm, used as an anomaly detector, built with a forest of deep decision trees on FPGA, field programmable gate arrays. Scenarios at the Large Hadron Collider at CERN are considered, for which the autoencoder is trained using known physical processes of the Standard Model. The design is then deployed in real-time trigger systems for anomaly detection of unknown physical processes, such as the detection of rare exotic decays of the Higgs boson. The inference is made with a latency value of 30 ns at percent-level resource usage using the Xilinx Virtex UltraScale+ VU9P FPGA. Our method offers anomaly detection at low latency values for edge AI users with resource constraints.

hep-ex↗

arXiv2022

Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics

We present a novel application of the machine learning / artificial intelligence method called boosted decision trees to estimate physical quantities on field programmable gate arrays (FPGA). The software package fwXmachina features a new architecture called parallel decision paths that allows for deep decision trees with arbitrary number of input variables. It also features a new optimization scheme to use different numbers of bits for each input variable, which produces optimal physics results and ultraefficient FPGA resource utilization. Problems in high energy physics of proton collisions at the Large Hadron Collider (LHC) are considered. Estimation of missing transverse momentum (ETmiss) at the first level trigger system at the High Luminosity LHC (HL-LHC) experiments, with a simplified detector modeled by Delphes, is used to benchmark and characterize the firmware performance. The firmware implementation with a maximum depth of up to 10 using eight input variables of 16-bit precision gives a latency value of O(10) ns, independent of the clock speed, and O(0.1)% of the available FPGA resources without using digital signal processors.

hep-ex↗

arXiv2021

Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics

We present a novel implementation of classification using the machine learning / artificial intelligence method called boosted decision trees (BDT) on field programmable gate arrays (FPGA). The firmware implementation of binary classification requiring 100 training trees with a maximum depth of 4 using four input variables gives a latency value of about 10 ns, independent of the clock speed from 100 to 320 MHz in our setup. The low timing values are achieved by restructuring the BDT layout and reconfiguring its parameters. The FPGA resource utilization is also kept low at a range from 0.01% to 0.2% in our setup. A software package called fwXmachina achieves this implementation. Our intended user is an expert of custom electronics-based trigger systems in high energy physics experiments or anyone that needs decisions at the lowest latency values for real-time event classification. Two problems from high energy physics are considered, in the separation of electrons vs. photons and in the selection of vector boson fusion-produced Higgs bosons vs. the rejection of the multijet processes.

hep-ex↗

arXiv2017

A new radiobiology-based HDR brachytherapy treatment planning algorithm used to investigate the potential for hypofractionation in cervical cancer

Most commercially available treatment planning systems for brachytherapy operate based on physical dose and do not incorporate fractionation or tissue-specific response. The purpose of this study is to investigate the potential for hypofractionation in HDR brachytherapy, thereby reducing the number of implants required. A new treatment planning algorithm was built in order to optimize based on tissue and fractionation specific parameters. Different fractionation schemes were considered for 6 patients, and plans were created using the new algorithm. A baseline fractionation scheme consisting of 5 fractions was compared to hypofractionated plans of 1 to 4 fractions. The effectiveness of each plan was evaluated using radiobiological criteria taken from GEC-ESTRO guidelines. The results of this study indicate that an optimization algorithm based on biological parameters has similar functionality to traditional planning methods with the additional ability to account for fractionation effects. Using this algorithm, it was shown that plans consisting of 3 and 4 fractions have comparable target coverage with equivalent normal tissue exposure. In some specific cases, further fractionation may present acceptable target coverage as well.

physics.med-ph↗

arXiv2017

Dark matter searches at the LHC

We present a summary of the current status of searches for dark matter at the LHC from the ATLAS and CMS experiments. For various assumptions in the simplified parameter space, the LHC exclusions is complementary to direct detection results. Mono-object analyses in search of dark matter and various analyses searching for dark matter mediators are presented.

hep-ex↗