Trainability ยท Algorithms
Orthogonal circuits exhibit a barren plateau
Theorem statement
For the circuit family whose dynamical Lie algebra is $\mathfrak{so}(2^n)$, the single-ideal loss variance $$\operatorname{Var}_\theta[\ell]=\frac{P_{\mathfrak g}(\rho)\,P_{\mathfrak g}(O)}{\dim\mathfrak g},\qquad \dim\mathfrak g=\frac{4^n-2^n}{2},$$ carries an algebra dimension that grows exponentially in the qubit count $n$. With the purities $P_{\mathfrak g}(\rho),\,P_{\mathfrak g}(O)$ bounded, the variance decays as $C\,b^{-n}$ with $b>1$, so the family exhibits a barren plateau.
Sources
- A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
Michael Ragone, Bojko N. Bakalov, Frederic Sauvage, Alexander F. Kemper, Carlos Ortiz Marrero, Martin Larocca, M. Cerezo, 2023
- Barren plateaus in quantum neural network training landscapes
Jarrod R. McClean, Sergio Boixo, Vadim N. Smelyanskiy, Ryan Babbush, Hartmut Neven, 2018
Lean context
- Lean declaration
QuantumAlg.soN_hasBarrenPlateau_schurDischarged
Copy a short prompt with the import, theorem name, citations, and public source link.