Pith. sign in

REVIEW 4 cited by

Spectral Reconstruction with Deep Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.04305 v2 pith:QUVJWPQE submitted 2019-05-10 physics.comp-ph cs.LGhep-lathep-ph

classification physics.comp-phcs.LGhep-lathep-ph
keywords reconstructiondataneuralapproachfunctionsinversemethodsnetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We explore artificial neural networks as a tool for the reconstruction of spectral functions from imaginary time Green's functions, a classic ill-conditioned inverse problem. Our ansatz is based on a supervised learning framework in which prior knowledge is encoded in the training data and the inverse transformation manifold is explicitly parametrised through a neural network. We systematically investigate this novel reconstruction approach, providing a detailed analysis of its performance on physically motivated mock data, and compare it to established methods of Bayesian inference. The reconstruction accuracy is found to be at least comparable, and potentially superior in particular at larger noise levels. We argue that the use of labelled training data in a supervised setting and the freedom in defining an optimisation objective are inherent advantages of the present approach and may lead to significant improvements over state-of-the-art methods in the future. Potential directions for further research are discussed in detail.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Operator Learning in Lattice QCD: Spectral Reconstruction

    hep-lat 2026-07 conditional novelty 7.0 of 10

    DeepONet ensembles trained on GP mock data reconstruct O(3) smeared spectral densities from lattice correlators with lower total uncertainty than HLT, consistent with the analytic result.

  2. Towards constraining QCD phase transitions in neutron star interiors: Bayesian Inference with TOV linear response analysis

    nucl-th 2025-01 conditional novelty 6.0 of 10

    A Bayesian framework with analytical TOV linear-response gradients and a neural-network equation of state reconstructs neutron star EoSs and constrains first-order phase transition parameters from simulated mass-radius data.

  3. Real-time dynamics from convex geometry

    hep-lat 2025-02 conditional novelty 3.0 of 10

    The paper derives model-independent, tight bounds on smeared real-time correlators from Euclidean lattice data by solving a finite-dimensional convex program.

  4. The spectral reconstruction problem for thermal photon and dilepton rates

    hep-ph 2025-08 unverdicted novelty 2.0 of 10

    A proceedings review presents an improved estimator (lambda = 2) and new lattice QCD estimates for the thermal photon production rate from quark-gluon plasma.

Pith tools