← 研踪 PaperTrailarXiv:2611.18378 · v1
Structure makes quantum circuits trainable
首次提交 2026-11-14 00:22
版本更新 2026-11-14 00:22
雷达观测 2026-11-16 11:41
摘要
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 and observables by decomposing the unitary representation of the associated compact Lie group. When the circuit segments on both sides of a gate form -designs, we obtain the variance exactly and prove a sufficient condition for trainability: if and 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 with the number of runs polynomial in , including cases in which the bounds are inconclusive. This resolves the question of the trainability of the circuit before expensive training procedures.
作者备注:83 pages, 4 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-14 00:22 · 最新观测版本
Structure makes quantum circuits trainable
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 and observables by decomposing the unitary representation of the associated compact Lie group. When the circuit segments on both sides of a gate form -designs, we obtain the variance exactly and prove a sufficient condition for trainability: if and 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 with the number of runs polynomial in , including cases in which the bounds are inconclusive. This resolves the question of the trainability of the circuit before expensive training procedures.
查看此版本解读 →查看此版本原文 ↗