betaFeedback

WorksPhysics and Astronomy

Structure makes quantum circuits trainable

Abstract

The scalability of variational quantum algorithms is limited by barren plateaus, where gradients vanish exponentially in system size. This worst-case result raises fundamental questions about the trainability of quantum AI models. We present a major advance towards resolving this trainability question by answering whether a given quantum circuit has a barren plateau. We do this using an analytical framework that bounds the gradient variance for arbitrary input states ρρ and observables M\mathcal{M} by decomposing the unitary representation of the associated compact Lie group. When the circuit segments on both sides of a gate form 22-designs, we obtain the variance exactly and prove a sufficient condition for trainability: if ρ⊗2ρ^{\otimes 2} and M⊗2\mathcal{M}^{\otimes 2} are sufficiently concentrated on the same irreducible invariant subspace of polynomial dimension, and the differentiated gate moves this subspace by an inverse-polynomial amount, then the gradient variance is at least inverse-polynomial. We further present a sampling algorithm that estimates the gradient variance from runs of the ansatz, without constructing the representation-theoretic projectors. Our algorithm decides whether the variance exceeds a tolerance ττ with the number of runs polynomial in 1/τ1/τ, including cases in which the bounds are inconclusive. This resolves the question of the trainability of the circuit before expensive training procedures.

Paper details

vlnc:W_hbj8pcgd
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 10

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Physics and Astronomy

Not recorded for this paper

View statement
Looking for related papers…