English

Quantum Natural Gradient

Quantum Physics 2020-05-27 v3 Machine Learning Machine Learning

Abstract

A quantum generalization of Natural Gradient Descent is presented as part of a general-purpose optimization framework for variational quantum circuits. The optimization dynamics is interpreted as moving in the steepest descent direction with respect to the Quantum Information Geometry, corresponding to the real part of the Quantum Geometric Tensor (QGT), also known as the Fubini-Study metric tensor. An efficient algorithm is presented for computing a block-diagonal approximation to the Fubini-Study metric tensor for parametrized quantum circuits, which may be of independent interest.

Keywords

Cite

@article{arxiv.1909.02108,
  title  = {Quantum Natural Gradient},
  author = {James Stokes and Josh Izaac and Nathan Killoran and Giuseppe Carleo},
  journal= {arXiv preprint arXiv:1909.02108},
  year   = {2020}
}

Comments

15 pages, 4 figures