Learning new physics from a machine
Explore this paper's citation graph
Summary
This work proposes using neural networks to detect data departures from a given reference model, with no prior bias on the nature of the new physics responsible for the discrepancy, and constructs an algorithm that implements this approach, as a straightforward application of the likelihood-ratio hypothesis test.
- Type
- article
- Published
- 2018-06-06
- Cited by
- 183
- References
- 79
- Access
- Open access
- OpenAlex
- https://openalex.org/W2807595580
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:50807342
Keywords
Monte Carlo method, Computer science, Artificial neural network, Set (abstract data type), Algorithm
References
- Anomaly Detection for Resonant New Physics with Machine Learning.
- Review of particle physics
- Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
- Pattern Recognition and Machine Learning
- Sleuth: A quasi-model-independent search strategy for new physics
- Playing tag with ANN: boosted top identification with pattern recognition
- A general search for new phenomena in ep scattering at HERA
- Limits and confidence intervals in the presence of nuisance parameters
- Approximation capabilities of multilayer feedforward networks
- Arbitrary nonlinearity is sufficient to represent all functions by neural networks: A theorem
- Semi-supervised anomaly detection – towards model-independent searches of new physics
- Tests of statistical hypotheses concerning several parameters when the number of observations is large
- Asymptotic formulae for likelihood-based tests of new physics
- The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses
- Model-Independent and Quasi-Model-Independent Search for New Physics at CDF
- Statistical Data Analysis
- Neural network parametrization of deep inelastic structure functions
- MUSiC—An Automated Scan for Deviations between Data and Monte Carlo Simulation
- General search for new phenomena in ep scattering at HERA
- Approximation by superpositions of a sigmoidal function
Cited by
- QCD-aware recursive neural networks for jet physics
- Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning
- Novelty Detection Meets Collider Physics
- Discovering physical concepts with neural networks
- Guiding new physics searches with unsupervised learning
- QCD or what?
- Searching for new physics with deep autoencoders
- An operational definition of quark and gluon jets
- Machine Learning for New Physics Searches
- Energy flow networks: deep sets for particle jets
- Variational autoencoders for new physics mining at the Large Hadron Collider
- Measuring Higgs Couplings without Higgs Bosons.
- Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions
- Interpretable deep learning for two-prong jet classification with jet spectra
- Searching for periodic signals in kinematic distributions using continuous wavelet transforms
- The motivation and status of two-body resonance decays after the LHC Run 2 and beyond
- Neural networks for full phase-space reweighting and parameter tuning
- Exploring anomalous couplings in Higgs boson pair production through shape analysis
- Exploring the space of jets with CMS open data
- Development of a ML-based model-independent analysis strategy at the LHC
Related papers
- The Monte Carlo Simulation of Tsinghua Homo-Source Dual-Beam Medical Accelerator
- PERAN RESIDEN ABDUL ROZAK PADA MASA REVOLUSI FISIK (1945 -1949)
- Two Radical Malays of Pahang During the Era of Struggle for Independence
- Spanish America after Independence, c.1820-c.1870
- The Independence of Albania
- The Development of the Monte Carlo Method for the Calculation of the Thermoluminescence Intensity and the Thermally Stimulated Conductivity
- The use of Monte Carlo simulation to evaluate optical properties of treated polyester fabric with TiO 2 nanopigments