Related papers: Amplitude Surrogates for Multi-Jet Processes
Ultra-fast, precise, and controlled amplitude surrogates are essential for future LHC event generation. First, we investigate the noise reduction and biases of network ensembles and outline a new method to learn well-calibrated systematic…
In this article we combine a recently proposed method for factorisation-aware matrix element surrogates with an unbiased unweighting algorithm. We show that employing a sophisticated neural network emulation of QCD multijet matrix elements…
Precision theoretical predictions for high multiplicity scattering rely on the evaluation of increasingly complicated scattering amplitudes which come with an extremely high CPU cost. For state-of-the-art processes this can cause technical…
Factorization underpins our ability to make predictions at the LHC, both in Monte Carlo simulations and direct calculations. An improved theoretical understanding of jet substructure can lead to calculations that can confront data and…
Higher-order theory predictions are crucial for the precision LHC program, but the time-consuming amplitude evaluation challenges the corresponding Monte-Carlo simulations. Machine-learned amplitude surrogates can resolve this problem, if…
The efficient simulation of multijet final states presents a serious computational task for analyses of LHC data and will be even more so at the HL-LHC. We here discuss means to accelerate the generation of unweighted events based on a…
Machine-intelligence has become a driving factor in modern society. However, its demand outpaces the underlying electronic technology due to limitations given by fundamental physics such as capacitive charging of wires, but also by system…
Evaluating loop amplitudes is a time-consuming part of LHC event generation. For di-photon production with jets we show that simple, Bayesian networks can learn such amplitudes and model their uncertainties reliably. A boosted training of…
The ALPHA algorithm to evaluate the exact, tree-level matrix elements is reviewed in the context of multi-parton processes in QCD. The algorithm is suited for the authomatic calculation of tree-level scattering amplitudes and allows for…
We study the factorization and resummation prediction on the jet mass spectrum in one-jet inclusive production at the LHC based on soft-collinear effective theory. The soft function with anti-$k_T$ algorithm is calculated at next-to-leading…
In this work, we consider scattering amplitudes relevant for high-precision Large Hadron Collider (LHC) phenomenology. We analyse the general structure of amplitudes, and we review state-of-the-art methods for computing them. We discuss…
Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale…
The search for signals of new physics at the forthcoming LHC experiments involves the analysis of final states characterised by a high number of hadronic jets or identified particles. Precise theoretical predictions for these processes…
We review the current status of high-multiplicity double-virtual QCD corrections to processes relevant for LHC phenomenology. In particular, we discuss the recent full-color calculation of the five-parton process, whose two-loop amplitudes…
Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with…
The factorization of multi-leg gauge theory amplitudes in the soft and collinear limits provides strong constraints on the structure of amplitudes, and enables efficient calculations of multi-jet observables at the LHC. There is significant…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…
High throughput and low latency data processing is essential for systems requiring live decision making, control, and machine learning-optimized data reduction. We focus on two distinct use cases for in-flight streaming data processing for…
Precision phenomenological studies of high-multiplicity scattering processes at collider experiments present a substantial theoretical challenge and are vitally important ingredients in experimental measurements. Machine learning technology…
End-to-end multilingual speech recognition involves using a single model training on a compositional speech corpus including many languages, resulting in a single neural network to handle transcribing different languages. Due to the fact…