English

Learned Optimizers for Analytic Continuation

Machine Learning 2022-02-07 v2 Statistical Mechanics Strongly Correlated Electrons

Abstract

Traditional maximum entropy and sparsity-based algorithms for analytic continuation often suffer from the ill-posed kernel matrix or demand tremendous computation time for parameter tuning. Here we propose a neural network method by convex optimization and replace the ill-posed inverse problem by a sequence of well-conditioned surrogate problems. After training, the learned optimizers are able to give a solution of high quality with low time cost and achieve higher parameter efficiency than heuristic fully-connected networks. The output can also be used as a neural default model to improve the maximum entropy for better performance. Our methods may be easily extended to other high-dimensional inverse problems via large-scale pretraining.

Keywords

Cite

@article{arxiv.2107.13265,
  title  = {Learned Optimizers for Analytic Continuation},
  author = {Dongchen Huang and Yi-feng Yang},
  journal= {arXiv preprint arXiv:2107.13265},
  year   = {2022}
}

Comments

11 pages, 7 figures, 6 tables