A Neural Bayesian Estimator for Conditional Probability Densities

Abstract

This article describes a robust algorithm to estimate a conditional probability density f(t|x) as a non-parametric smooth regression function. It is based on a neural network and the Bayesian interpretation of the network output as a posteriori probabability. The network is trained using example events from history or simulation, which define the underlying probability density f(t,x). Once trained, the network is applied on new, unknown examples x, for which it can predict the probability distribution of the target variable t. Event-by-event knowledge of the smooth function f(t|x) can be very useful, e.g. in maximum likelihood fits or for forecasting tasks. No assumptions are necessary about the distribution, and non-Gaussian tails are accounted for automatically. Important quantities like median, mean value, left and right standard deviations, moments and expectation values of any function of t are readily derived from it. The algorithm can be considered as an event-by-event unfolding and leads to statistically optimal reconstruction. The largest benefit of the method lies in complicated problems, when the measurements x are only relatively weakly correlated to the output t. As to assure optimal generalisation features and to avoid overfitting, the networks are regularised by extended versions of weight decay. The regularisation parameters are determined during the online-learning of the network by relations obtained from Bayesian statistics. Some toy Monte Carlo tests and first real application examples from high-energy physics and econometry are discussed.

26 pages, 9 figures. This article is a reprint of an internal EKP note from January 2001, corrected and supplemented by information on the development in the 3 years since then. The algorithm is implemented and further developed in the NeuroBayes package by Phi-T Physics Information Technologies GmbH, Karlsruhe, Germany

References in corpus (2)

• A Precise Measurement of the B+, B0 and Mean b-hadron Lifetime with the DELPHI Detector at LEP I
• BSAURUS- A Package For Inclusive B-Reconstruction in DELPHI

Cited by in corpus (20)

• Measurement of the single-top-quark t-channel cross section in pp collisions at sqrt(s) = 7 TeV
• Measurement of the t-channel single top-quark production cross section in pp collisions at sqrt(s) = 7 TeV with the ATLAS detector
• Search for the decays $B_s^0\to {\tau }^{+}{\tau }^{-}$ and $B^0\to {\tau }^{+}{\tau }^{-}$
• A Hierarchical NeuroBayes-based Algorithm for Full Reconstruction of B Mesons at B Factories
• Measurement of the inclusive cross-sections of single top-quark and top-antiquark $t$-channel production in $pp$ collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector
• Measurement of the production cross-section of a single top quark in association with a $Z$ boson in proton--proton collisions at 13 TeV with the ATLAS detector
• Measurement of the differential branching fraction of the decay ${\Lambda }_b^0\to \Lambda {\mu }^{+}{\mu }^{-}$
• Observation of the ${\Lambda }_b^0\to J/\psi p{\pi }^{-}$ decay
• Observation of the associated production of a top quark and a $Z$ boson in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
• Machine Learning in High Energy Physics Community White Paper
• Measurement of the ${\Lambda }_b^0\to J/\psi \Lambda$ angular distribution and the ${\Lambda }_b^0$ polarisation in $pp$ collisions
• Measurement of the time-dependent CP asymmetries in $B_s^0\to J/\psi K_{\mathrm{S}}^0$
• Measurement of the inclusive and fiducial $t\bar{t}$ production cross-sections in the lepton+jets channel in $pp$ collisions at $\sqrt{s}=8$ TeV with the ATLAS detector
• Measurement of the effective B_s^0 -> J/ψ K_S^0 lifetime
• Measurement of single top-quark production in association with a $W$ boson in the single-lepton channel at $\sqrt{s}=8$ TeV with the ATLAS detector
• Les Houches guide to reusable ML models in LHC analyses
• The use of adversaries for optimal neural network training
• An implicit function learning approach for parametric modal regression
• Experimental Studies of Top Quark Production