skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Uncertainty quantification for wide-bin unfolding: one-at-a-time strict bounds and prior-optimized confidence intervals
Abstract Unfolding is an ill-posed inverse problem in particle physics aiming to infer a true particle-level spectrum from smeared detector-level data. For computational and practical reasons, these spaces are typically discretized using histograms, and the smearing is modeled through a response matrix corresponding to a discretized smearing kernel of the particle detector. This response matrix depends on the unknown shape of the true spectrum, leading to a fundamental systematic uncertainty in the unfolding problem. To handle the ill-posed nature of the problem, common approaches regularize the problem either directly via methods such as Tikhonov regularization, or implicitly by using wide-bins in the true space that match the resolution of the detector. Unfortunately, both of these methods lead to a non-trivial bias in the unfolded estimator, thereby hampering frequentist coverage guarantees for confidence intervals constructed from these methods. We propose two new approaches to addressing the bias in the wide-bin setting through methods called One-at-a-time Strict Bounds (OSB) and Prior-Optimized (PO) intervals. The OSB intervals are a bin-wise modification of an existing guaranteed-coverage procedure, while the PO intervals are based on a decision-theoretic view of the problem. Importantly, both approaches provide well-calibrated frequentist confidence intervals even in constrained and rank-deficient settings. These methods are built upon a more general answer to the wide-bin bias problem, involving unfolding with fine bins first, followed by constructing confidence intervals for linear functionals of the fine-bin counts. We test and compare these methods to other available methodologies in a wide-bin deconvolution example and a realistic particle physics simulation of unfolding a steeply falling particle spectrum.  more » « less
Award ID(s):
2053804 2020295
PAR ID:
10430508
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Journal of Instrumentation
Volume:
17
Issue:
10
ISSN:
1748-0221
Page Range / eLocation ID:
P10013
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Physical Review D)
    Deconvolving (“unfolding”) detector distortions is a critical step in the comparison of cross-section measurements with theoretical predictions in particle and nuclear physics. However, most existing approaches require histogram binning while many theoretical predictions are at the level of statistical moments. We develop a new approach to directly unfold distribution moments as a function of another observable without having to first discretize the data. Our moment unfolding technique uses machine learning and is inspired by Boltzmann weight factors and generative adversarial networks (GANs). We demonstrate the performance of this approach using jet substructure measurements in collider physics. With this illustrative example, we find that our moment unfolding protocol is more precise than bin-based approaches and is as or more precise than completely unbinned methods. Published by the American Physical Society2024 
    more » « less
  2. ; (, Sensors)
    Energy-resolving photon-counting detectors (PCDs) separate photons from a polychromatic X-ray source into a number of separate energy bins. This spectral information from PCDs would allow advancements in X-ray imaging, such as improving image contrast, quantitative imaging, and material identification and characterization. However, aspects like detector spectral distortions and scattered photons from the object can impede these advantages if left unaccounted for. Scattered X-ray photons act as noise in an image and reduce image contrast, thereby significantly hindering PCD utility. In this paper, we explore and outline several important characteristics of spectral X-ray scatter with examples of soft-material imaging (such as cancer imaging in mammography or explosives detection in airport security). Our results showed critical spectral signatures of scattered photons that depend on a few adjustable experimental factors. Additionally, energy bins over a large portion of the spectrum exhibit lower scatter-to-primary ratio in comparison to what would be expected when using a conventional energy-integrating detector. These important findings allow flexible choice of scatter-correction methods and energy-bin utilization when using PCDs. Our findings also propel the development of efficient spectral X-ray scatter correction methods for a wide range of PCD-based applications. 
    more » « less
  3. ; ; (, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics (AITSTAS))
    The goal of this paper is to develop a practical and general-purpose approach to construct confidence intervals for differentially private parametric estimation. We find that the parametric bootstrap is a simple and effective solution. It cleanly reasons about variability of both the data sample and the randomized privacy mechanism and applies "out of the box" to a wide class of private estimation routines. It can also help correct bias caused by clipping data to limit sensitivity. We prove that the parametric bootstrap gives consistent confidence intervals in two broadly relevant settings, including a novel adaptation to linear regression that avoids accessing the covariate data multiple times. We demonstrate its effectiveness for a variety of estimators, and find empirically that it provides confidence intervals with good coverage even at modest sample sizes and performs better than alternative approaches. 
    more » « less
  4. ; ; (, Biometrika)
    Debiased machine learning is a meta-algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i.e., scalar summaries, of machine learning algorithms. For example, an analyst may seek the confidence interval for a treatment effect estimated with a neural network. We present a non-asymptotic debiased machine learning theorem that encompasses any global or local functional of any machine learning algorithm that satisfies a few simple, interpretable conditions. Formally, we prove consistency, Gaussian approximation and semiparametric efficiency by finite-sample arguments. The rate of convergence is $$n^{-1/2}$$ for global functionals, and it degrades gracefully for local functionals. Our results culminate in a simple set of conditions that an analyst can use to translate modern learning theory rates into traditional statistical inference. The conditions reveal a general double robustness property for ill-posed inverse problems. 
    more » « less
  5. (, Monthly Notices of the Royal Astronomical Society)
    ABSTRACT A popular numerical method to model the dynamics of a ‘full spectrum’ of cosmic rays (CRs), also applicable to radiation/neutrino hydrodynamics, is to discretize the spectrum at each location/cell as a piecewise power law in ‘bins’ of momentum (or frequency) space. This gives rise to a pair of conserved quantities (e.g. CR number and energy) that are exchanged between cells or bins, which in turn give the update to the normalization and slope of the spectrum in each bin. While these methods can be evolved exactly in momentum-space (e.g. considering injection, absorption, continuous losses/gains), numerical challenges arise dealing with spatial fluxes, if the scattering rates depend on momentum. This has often been treated either by neglecting variation of those rates ‘within the bin,’ or sacrificing conservation – introducing significant errors. Here, we derive a rigorous treatment of these terms, and show that the variation within the bin can be accounted for accurately with a simple set of scalar correction coefficients that can be written entirely in terms of other, explicitly evolved ‘bin-integrated’ quantities. This eliminates the relevant errors without added computational cost, has no effect on the numerical stability of the method, and retains manifest conservation. We derive correction terms both for methods that explicitly integrate flux variables (e.g. two-moment or M1-like) methods, as well as single-moment (advection-diffusion, FLD-like) methods, and approximate corrections valid in various limits. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email