Variational algorithms ยท Analysis
Generalized parameter-shift rule
Theorem statement
Given a Hermitian observable $O$, a Hermitian generator $G$
with eigenvalues $\{\omega_j\}_{j\in[d]}$, the single-parameter
gate $U(x) = e^{ixG}$, and a pure state $|\psi\rangle$,
consider the loss
$\ell(x) = \langle\psi| U^\dagger(x) O U(x) |\psi\rangle$.
Let $\{\Omega_p\}_{p\in[R]} :=
\{\omega_k - \omega_j : j,k\in[d], \omega_k > \omega_j\}$
be the $R$ unique positive eigenvalue differences of $G$,
where $R\geq1$.
Assuming these frequencies are equidistant integers
$\Omega_p = p$ (without loss of generality, by rescaling),
the first and second derivatives of $\ell$ at the origin
are given by the generalized parameter-shift rule
$$
\begin{aligned}
\ell'(0)
&= \sum_{\mu=1}^{2R}
\ell\left(\frac{2\mu-1}{2R}\pi\right)
\frac{(-1)^{\mu-1}}
{4R \sin^2\left(\frac{2\mu-1}{4R}\pi\right)},\\
\ell''(0)
&= -\ell(0)\frac{2R^2+1}{6}
+ \sum_{\mu=1}^{2R-1}
\ell\left(\frac{\mu\pi}{R}\right)
\frac{(-1)^{\mu-1}}
{2\sin^2\left(\frac{\mu\pi}{2R}\right)}.
\end{aligned}
$$
For $R=1$ and $R=2$ these reduce to the standard two-term
and four-term parameter-shift rules.
Sources
- General parameter-shift rules for quantum gradients
David Wierichs, Josh Izaac, Cody Wang, Cedric Yen-Yu Lin, 2022
Lean context
- Lean declaration
QuantumAlg.GeneralizedParamShift.quantumMain
Copy a short prompt with the import, theorem name, citations, and public source link.