A Cautionary Tale of Decorrelating Theory Uncertainties
arXiv:2109.08159 · doi:10.1140/epjc/s10052-022-10012-w
Abstract
A variety of techniques have been proposed to train machine learning classifiers that are independent of a given feature. While this can be an essential technique for enabling background estimation, it may also be useful for reducing uncertainties. We carefully examine theory uncertainties, which typically do not have a statistical origin. We will provide explicit examples of two-point (fragmentation modeling) and continuous (higher-order corrections) uncertainties where decorrelating significantly reduces the apparent uncertainty while the actual uncertainty is much larger. These results suggest that caution should be taken when using decorrelation for these types of uncertainties as long as we do not have a complete decomposition into statistically meaningful components.
arXiv comment19 pages, 8 figures. v2: added to acknowledgements
References in corpus (62)
- Adam: A Method for Stochastic Optimization
- PYTHIA 6.4 Physics and Manual
- PYTHIA 6.2 Physics and Manual
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- The anti-k_t jet clustering algorithm
- A Brief Introduction to PYTHIA 8.1
- FastJet user manual
- DELPHES 3, A modular framework for fast simulation of a generic collider experiment
- Machine learning and the physical sciences
- Measuring and testing dependence by correlation of distances
- Event generation with SHERPA 1.1
- Herwig++ Physics and Manual
- Parton distributions with LHC data
- Dispelling the N^3 myth for the Kt jet-finder
- Herwig 7.0 / Herwig++ 3.0 Release Note
- Jet substructure as a new Higgs search channel at the LHC
- Event Generation with Sherpa 2.2
- Identifying Boosted Objects with N-subjettiness
- Brownian distance covariance
- Soft Drop
- Jet Trimming
- Towards an understanding of jet substructure
- Energy Correlation Functions for Jet Substructure
- Deep Learning and its Application to LHC Physics
- Jet substructure as a new Higgs search channel at the LHC
- Maximizing Boosted Top Identification by Minimizing N-subjettiness
- Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
- Recombination Algorithms and Jet Substructure: Pruning as a Tool for Heavy Particle Searches
- Jet-Images -- Deep Learning Edition
- The Machine Learning Landscape of Top Taggers
- Parameterized Machine Learning for High-Energy Physics
- Power Counting to Better Jet Observables
- A modified cluster-hadronization model
- Mining gold from implicit models to improve likelihood-free inference
- Constraining Effective Field Theories with Machine Learning
- Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
- What is the Machine Learning?
- A Guide to Constraining Effective Field Theories with Machine Learning
- Machine and Deep Learning Applications in Particle Physics
- Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
- Nuisance hardened data compression for fast likelihood-free inference
- Automatic physical inference with information maximising neural networks
- Performance of top-quark and -boson tagging with ATLAS in Run 2 of the LHC
- Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
- Learning to Pivot with Adversarial Networks
- DisCo Fever: Robust Networks Through Distance Correlation
- Machine Learning Uncertainties with Adversarial Neural Networks
- Measurement of the inclusive cross-sections of single top-quark and top-antiquark -channel production in collisions at = 13 TeV with the ATLAS detector
- ABCDisCo: Automating the ABCD Method with Machine Learning
- A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
- A deep neural network to search for new long-lived particles decaying to jets
- Uncertainty Aware Learning for High Energy Physics
- INFERNO: Inference-Aware Neural Optimisation
- uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
- Convolved Substructure: Analytically Decorrelating Jet Substructure Observables
- Mass Agnostic Jet Taggers
- QBDT, a new boosting decision tree method with systematic uncertainties into training for High Energy Physics
- Measurement of differential cross sections and charge ratios for -channel single top quark production in proton-proton collisions at 13 TeV
- Reducing the dependence of the neural network function to systematic uncertainties in the input space
- Optimal statistical inference in the presence of systematic uncertainties using neural network optimization based on binned Poisson likelihoods with nuisance parameters
- Enhancing searches for resonances with machine learning and moment decomposition
- New approaches for boosting to uniformity