• Corpus ID: 234339652

Scaffolding Simulations with Deep Learning for High-dimensional Deconvolution

@article{Andreassen2021ScaffoldingSW,
  title={Scaffolding Simulations with Deep Learning for High-dimensional Deconvolution},
  author={Anders Johan Andreassen and Patrick T. Komiske and Eric M. Metodiev and Benjamin Philip Nachman and Adithya Suresh and Jesse Thaler},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.04448}
}
A common setting for scientific inference is the ability to sample from a highfidelity forward model (simulation) without having an explicit probability density of the data. We propose a simulation-based maximum likelihood deconvolution approach in this setting called OMNIFOLD. Deep learning enables this approach to be naturally unbinned and (variable-, and) high-dimensional. In contrast to model parameter estimation, the goal of deconvolution is to remove detector distortions in order to… 

Figures and Tables from this paper

Neural conditional reweighting
TLDR
This paper applies neural conditional reweighting to the energy response of high-energy jets, which could be used to improve the modeling of physics objects in parametrized fast simulation packages and yields sensible interpolation even in the presence of phase space holes.
Optimizing Observables with Machine Learning for Better Unfolding
TLDR
It is pointed out that while the particle-level observable needs to be physically motivated to link with theory, the detector-level need not be and can be optimized.
Publishing unbinned differential cross section results
TLDR
This paper is to propose a scheme for presenting and using unbinned results, which can hopefully form the basis for a community standard to allow for integration into analysis workflows.
Reconstructing the kinematics of deep inelastic scattering with deep learning
Machine Learning and LHC Event Generation
First-principle simulations are at the heart of the high-energy physics research program. They link the vast data output of multi-purpose detectors with fundamental theory predictions and
Disentangling Quarks and Gluons with CMS Open Data
We study quark and gluon jets separately using public collider data from the CMS experiment. Our analysis is based on 2 . 3 fb − 1 of proton-proton collisions at √ s = 7 TeV, collected at the Large

References

SHOWING 1-10 OF 19 REFERENCES
Neural resampler for Monte Carlo reweighting with preserved uncertainties
Monte Carlo event generators are an essential tool for data analysis in collider physics. To include subleading quantum corrections, these generators often need to produce negative weight events,
Unification of Deconvolution Algorithms for Cherenkov Astronomy
TLDR
This work presents a novel unified view on deconvolution methods, rephrasing them in the language of data science, and proposes a novel stopping condition that guarantees fast convergence.
OmniFold: A Method to Simultaneously Unfold All Observables.
TLDR
OmniFold, an unfolding method that iteratively reweights a simulated dataset, using machine learning to capitalize on all available information, is introduced, which enables the simultaneous measurement of all observables, including those not yet invented at the time of the analysis.
Energy flow networks: deep sets for particle jets
TLDR
Adapting and specializing the “Deep Sets” framework to particle physics, Energy Flow Networks are introduced, which respect infrared and collinear safety by construction and also develop Particle Flow Networks, which allow for general energy dependence and the inclusion of additional particle-level information such as charge and flavor.
Adam: A Method for Stochastic Optimization
TLDR
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Machine learning approach to inverse problem and unfolding procedure
A procedure for unfolding the true distribution from experimental data is presented. Machine learning method are applied for the identiflcation an apparatus function and solving inverse problem
How to GAN away detector effects
TLDR
This work shows how simulations, for instance, of detector effects can instead be inverted using generative networks, and illustrates how, in general, fully conditional generative Networks can statistically invert Monte Carlo simulations.
Machine learning as an instrument for data unfolding
TLDR
A method for correcting for detector smearing effects using machine learning techniques is presented and can use more than one reconstructed variable to infere the value of the unsmeared quantity on event by event basis.
Invertible networks or partons to detector and back again
TLDR
This work unfolds detector effects and QCD radiation to a pre-defined hard process with a per-event probabilistic interpretation over parton-level phase space, and allows for a variable number of QCD jets.
...
...