Riemannian modified Newton optimization on quantum search achieves quadratic convergence and O(√(N/M) log log(1/ε)) complexity when M/N is known.
Randomized gradient de- scents on riemannian manifolds: Almost sure convergence to global minima in and beyond quantum optimization
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Loss-aware natural gradient variants are introduced by embedding the loss hypersurface in a statistical manifold or using quantum state overlaps, yielding conformal updates that adjust effective step size.
Unifies fixed-ansatz and adaptive VQE via ansatz-free product-unitary formulation on the unitary group and derives convergence rates, initialization guarantees, and noise-robust measurement strategies for Riemannian gradient descent.
citing papers explorer
-
Achieving double-logarithmic precision dependence in optimization-based quantum unstructured search
Riemannian modified Newton optimization on quantum search achieves quadratic convergence and O(√(N/M) log log(1/ε)) complexity when M/N is known.
-
Loss-aware state space geometry for quantum variational algorithms
Loss-aware natural gradient variants are introduced by embedding the loss hypersurface in a statistical manifold or using quantum state overlaps, yielding conformal updates that adjust effective step size.
-
Geometric Analysis of Variational Quantum Eigensolver
Unifies fixed-ansatz and adaptive VQE via ansatz-free product-unitary formulation on the unitary group and derives convergence rates, initialization guarantees, and noise-robust measurement strategies for Riemannian gradient descent.