What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric

Key points

• Either convention could decide whether an optimizer's costlier steps pay off.1
• We measure how much each convention changes verdicts among Adam, simultaneous perturbation stochastic approximation (SPSA) and quantum natural gradient (QNG), on initializations held out from the selection of settings.1
• We compute the exact metric that preconditions QNG, price every step in circuit evaluations and give every method the same budget.1
• QNG's strict-target lead disappears when the metric's simulator price, linear in the number of parameters, is replaced by an assumed hardware count quadratic in that number.1

Sources (1)

• [1]What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed Metric
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:24 AM

  Several published comparisons of variational quantum optimizers time only runs that reach a target loss, or read the verdict at a single target.

  Either convention could decide whether an optimizer's costlier steps pay off.

Extractive summary: sentences quoted from the sources.