Spectral Reconstruction with Deep Neural Networks

@article{Kades2019SpectralRW,
  title={Spectral Reconstruction with Deep Neural Networks},
  author={Lukas Kades and Jan M. Pawlowski and Alexander Rothkopf and Manuel Scherzer and Jeffrey J. Urban and Sebastian Johann Wetzel and Nicolas Wink and Felix P.G. Ziegler},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.04305}
}
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… CONTINUE READING
3
Twitter Mentions