G. Grosso
YOU?
Author Swipe
View article: Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies
Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies Open
Modern artificial intelligence has revolutionized our ability to extract rich and versatile data representations across scientific disciplines. Yet, the statistical properties of these representations remain poorly controlled, causing miss…
View article: Robust resonant anomaly detection with NPLM
Robust resonant anomaly detection with NPLM Open
In this study, we investigate the application of the New Physics Learning Machine (NPLM) algorithm as an alternative to the standard CWoLa method with Boosted Decision Trees (BDTs), particularly for scenarios with rare signal events. NPLM …
View article: Anomaly-preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC
Anomaly-preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC Open
Anomaly detection—identifying deviations from Standard Model predictions—is a key challenge at the Large Hadron Collider due to the size and complexity of its datasets. This is typically addressed by transforming high-dimensional detector …
View article: Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC
Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC Open
Anomaly detection -- identifying deviations from Standard Model predictions -- is a key challenge at the Large Hadron Collider due to the size and complexity of its datasets. This is typically addressed by transforming high-dimensional det…
View article: Multiple testing for signal-agnostic searches for new physics with machine learning
Multiple testing for signal-agnostic searches for new physics with machine learning Open
In this work, we address the question of how to enhance signal-agnostic searches by leveraging multiple testing strategies. Specifically, we consider hypothesis tests relying on machine learning, where model selection can introduce a bias …
View article: Robust resonant anomaly detection with NPLM
Robust resonant anomaly detection with NPLM Open
In this study, we investigate the application of the New Physics Learning Machine (NPLM) algorithm as an alternative to the standard CWoLa method with Boosted Decision Trees (BDTs), particularly for scenarios with rare signal events. NPLM …
View article: Anomaly-aware summary statistic from data batches
Anomaly-aware summary statistic from data batches Open
A bstract Signal-agnostic data exploration based on machine learning could unveil very subtle statistical deviations of collider data from the expected Standard Model of particle physics. The beneficial impact of a large training sample on…
View article: Product Manifold Machine Learning for Physics
Product Manifold Machine Learning for Physics Open
Physical data are representations of the fundamental laws governing the Universe, hiding complex compositional structures often well captured by hierarchical graphs. Hyperbolic spaces are endowed with a non-Euclidean geometry that naturall…
View article: Assessment of a space and energy resolved diagnostic based on GEM technology on MAST-U
Assessment of a space and energy resolved diagnostic based on GEM technology on MAST-U Open
A gas electron multiplier (GEM)-based detector was utilized for the first time on a spherical tokamak, MAST-U, during the 2023 campaign to investigate soft x-ray (SXR) radiation (1–20 keV) emitted from the plasma. GEM detectors, chosen for…
View article: Multiple testing for signal-agnostic searches of new physics with machine learning
Multiple testing for signal-agnostic searches of new physics with machine learning Open
In this work, we address the question of how to enhance signal-agnostic searches by leveraging multiple testing strategies. Specifically, we consider hypothesis tests relying on machine learning, where model selection can introduce a bias …
View article: Anomaly-aware summary statistic from data batches
Anomaly-aware summary statistic from data batches Open
Signal-agnostic data exploration based on machine learning could unveil very subtle statistical deviations of collider data from the expected Standard Model of particle physics. The beneficial impact of a large training sample on machine l…
View article: Goodness of fit by Neyman-Pearson testing
Goodness of fit by Neyman-Pearson testing Open
The Neyman-Pearson strategy for hypothesis testing can be employed for goodness of fit if the alternative hypothesis is selected from data by exploring a rich parametrised family of models, while controlling the impact of statistical fluct…
View article: Report on scipost_202307_00009v1
Report on scipost_202307_00009v1 Open
The Neyman-Pearson strategy for hypothesis testing can be employed for goodness of fit if the alternative hypothesis is generic enough not to introduce a significant bias while at the same time avoiding overfitting.A practical implementati…
View article: Report on scipost_202307_00009v1
Report on scipost_202307_00009v1 Open
The Neyman-Pearson strategy for hypothesis testing can be employed for goodness of fit if the alternative hypothesis is generic enough not to introduce a significant bias while at the same time avoiding overfitting.A practical implementati…
View article: Triggerless data acquisition pipeline for Machine Learning based statistical anomaly detection
Triggerless data acquisition pipeline for Machine Learning based statistical anomaly detection Open
This work describes an online processing pipeline designed to identify anomalies in a continuous stream of data collected without external triggers from a particle detector. The processing pipeline begins with a local reconstruction algori…
View article: Triggerless data acquisition pipeline for Machine Learning based statistical anomaly detection
Triggerless data acquisition pipeline for Machine Learning based statistical anomaly detection Open
This work describes an online processing pipeline designed to identify anomalies in a continuous stream of data collected without external triggers from a particle detector. The processing pipeline begins with a local reconstruction algori…
View article: Fast kernel methods for data quality monitoring as a goodness-of-fit test
Fast kernel methods for data quality monitoring as a goodness-of-fit test Open
We propose an accurate and efficient machine learning approach for monitoring particle detectors in real-time. The goal is to assess the compatibility of incoming experimental data with a reference dataset, characterising the data behaviou…
View article: Goodness of fit by Neyman-Pearson testing
Goodness of fit by Neyman-Pearson testing Open
The Neyman-Pearson strategy for hypothesis testing can be employed for goodness of fit if the alternative hypothesis is selected from data by exploring a rich parametrised family of models, while controlling the impact of statistical fluct…
View article: Analytical and MonteCarlo approaches to infer the total gamma ray emission from the JET tokamak
Analytical and MonteCarlo approaches to infer the total gamma ray emission from the JET tokamak Open
A single gamma-ray spectrometer installed at the end of a collimator can be used to infer the total emission from a tokamak plasma if the transport of gamma-rays from the plasma to the detector is known. In such analysis, the plasma emissi…
View article: Fast kernel methods for Data Quality Monitoring as a goodness-of-fit test
Fast kernel methods for Data Quality Monitoring as a goodness-of-fit test Open
We here propose a machine learning approach for monitoring particle detectors in real-time. The goal is to assess the compatibility of incoming experimental data with a reference dataset, characterising the data behaviour under normal circ…
View article: The Analytical Method algorithm for trigger primitives generation at the LHC Drift Tubes detector
The Analytical Method algorithm for trigger primitives generation at the LHC Drift Tubes detector Open
View article: A fast and flexible machine learning approach to data quality monitoring
A fast and flexible machine learning approach to data quality monitoring Open
We present a machine learning based approach for real-time monitoring of particle detectors. The proposed strategy evaluates the compatibility between incoming batches of experimental data and a reference sample representing the data behav…
View article: A 40 MHz Level-1 trigger scouting system for the CMS Phase-2 upgrade
A 40 MHz Level-1 trigger scouting system for the CMS Phase-2 upgrade Open
View article: Learning new physics efficiently with nonparametric methods
Learning new physics efficiently with nonparametric methods Open
We present a machine learning approach for model-independent new physics searches. The corresponding algorithm is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any c…
View article: DQM for Drift Tube Chambers
DQM for Drift Tube Chambers Open
Dataset for DQM for Drift Tube Chambers. The dataset include a reference sample and smaller data samples characterized by anomalous effects. Plots for data visualization are provided.
View article: DQM for Drift Tube Chambers
DQM for Drift Tube Chambers Open
Dataset for DQM for Drift Tube Chambers. The dataset include a reference sample and smaller data samples characterized by anomalous effects. Plots for data visualization are provided.
View article: Learning new physics efficiently with nonparametric methods
Learning new physics efficiently with nonparametric methods Open
We present a machine learning approach for model-independent new physics searches. The corresponding algorithm is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any c…
View article: Learning new physics from an imperfect machine
Learning new physics from an imperfect machine Open
We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment o…
View article: Learning New Physics from an Imperfect Machine
Learning New Physics from an Imperfect Machine Open
We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment o…
View article: NPLM: Learning Multivariate New Physics
NPLM: Learning Multivariate New Physics Open
Archive of synthetic data used for the studies presented in arXiv:1912.12155