On the Computational Complexity of Geometrically Local QAC0 circuits

• URL: http://arxiv.org/abs/2604.07178v1
• Date: Wed, 08 Apr 2026 15:07:09 GMT
• Title: On the Computational Complexity of Geometrically Local QAC0 circuits
• Abstract summary: We show that any $mathsfQAC0$ circuit can be exactly simulated by a two-dimensional geometrically local $mathsfQAC0$ circuit.<n>We prove a nearly logarithmic depth lower bound on $mathsf1Dtext-QAC0 $ circuits to compute the Parity function.
• Score: 13.101369903953804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The computational complexity of $\mathsf{QAC}^0$, which are constant-depth, polynomial-size quantum circuit families consisting of arbitrary single-qubit unitaries and $n$-qubit generalized Toffoli gates, has gained tremendous focus recently. In this work, we initiate the study of the computational complexity of geometrically local $\mathsf{QAC}^0$ circuits, where all the generalized Toffoli gates act on nearest neighbor qubits. We show that any $\mathsf{QAC}^0$ circuit can be exactly simulated by a two-dimensional geometrically local $\mathsf{QAC}^0$ circuit, i.e., a $\mathsf{2D\text{-}QAC}^{0}$ circuit, with a quadratic size blow-up. This implies that $\mathsf{QAC}^0 = \mathsf{2D\text{-}QAC}^{0}$. We further show that if there existed a $\mathsf{QAC}^0$ circuit that computes Parity with a bounded constant error, then for any $\varepsilon > 0$, there would exist a $\mathsf{2D\text{-}QAC}^{0}$ circuit that exactly computes Parity, with a very "thin" width $n^\varepsilon$. We further study the computational power of $\mathsf{1D\text{-}QAC}^{0} $ circuits, i.e., one-dimensional $\mathsf{QAC}^0$ circuits, which are the "thinnest" $\mathsf{2D\text{-}QAC}^{0}$ circuits. We prove a nearly logarithmic depth lower bound on $\mathsf{1D\text{-}QAC}^{0} $ circuits to compute the Parity function, even if allowing an unlimited number of ancilla. Furthermore, if the inputs are encoded in contiguous qubits, we prove that it requires a nearly linear depth $\mathsf{1D\text{-}QAC}^{0} $ circuit to compute the Parity function. This lower bound is almost tight. The results are proved via the combination of the restriction argument and the light-cone argument. These results may provide a new angle for studying the computational power of $\mathsf{QAC}^0$ circuits and for resolving the long-standing open problem of whether Parity is in $\mathsf{QAC}^0$.

Related papers

• QAC0 Can Prepare Every Logarithmic-Qubit State [1.4018975578160688]
  $mathsfQAC0$ is the class of constant-depth $mathrmpoly(n)$-ancilla circuits.<n>We show that every $O(log n)$-qubit state can be exactly and cleanly prepared by a $mathrmpoly(n)$-ancilla $mathsfQAC0$ circuit.
  arXiv  Detail & Related papers  (2026-09-15T16:35:52Z)
• $\mathsf{QAC}^0$ Contains $\mathsf{TC}^0$ (with Many Copies of the Input) [0.9023122463034333]
  $mathsfQAC0$ is the class of constant-depth quantum circuits constructed from arbitrary single-qubit gates and generalized Toffoli gates.<n>We show that $mathsfQAC0$ circuits are significantly more powerful than their classical counterparts.
  arXiv  Detail & Related papers  (2026-01-06T18:40:44Z)
• Low-degree approximation of QAC$^0$ circuits [0.0]
  We show that the parity function cannot be computed in QAC$0$. We also show that any QAC circuit of depth $d$ that approximately computes parity on $n$ bits requires $2widetildeOmega(n1/d)$.
  arXiv  Detail & Related papers  (2024-11-01T19:04:13Z)
• The Communication Complexity of Approximating Matrix Rank [50.6867896228563]
  We show that this problem has randomized communication complexity $Omega(frac1kcdot n2log|mathbbF|)$. As an application, we obtain an $Omega(frac1kcdot n2log|mathbbF|)$ space lower bound for any streaming algorithm with $k$ passes.
  arXiv  Detail & Related papers  (2024-10-26T06:21:42Z)
• On the Computational Power of QAC0 with Barely Superlinear Ancillae [10.737102385599169]
  We show that any depth-$d$ $mathrmQAC0$ circuit requires $n1+3-d$ ancillae to compute a function with approximate degree $ta(n)$.<n>This is the first superlinear lower bound on the super-linear sized $mathrmQAC0$.
  arXiv  Detail & Related papers  (2024-10-09T02:55:57Z)
• Provably learning a multi-head attention layer [55.2904547651831]
  Multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models. In this work, we initiate the study of provably learning a multi-head attention layer from random examples. We prove computational lower bounds showing that in the worst case, exponential dependence on $m$ is unavoidable.
  arXiv  Detail & Related papers  (2024-02-06T15:39:09Z)
• On the Pauli Spectrum of QAC0 [2.3436632098950456]
  We conjecture that the Pauli spectrum of $mathsfQAC0$ satisfies low-degree concentration. We obtain new circuit lower bounds and learning results as applications.
  arXiv  Detail & Related papers  (2023-11-16T07:25:06Z)
• Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization [54.29685789885059]
  We introduce efficient $(1+varepsilon)$-approximation algorithms for the binary matrix factorization (BMF) problem. The goal is to approximate $mathbfA$ as a product of low-rank factors. Our techniques generalize to other common variants of the BMF problem.
  arXiv  Detail & Related papers  (2023-06-02T18:55:27Z)
• Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
  We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
  arXiv  Detail & Related papers  (2022-06-17T17:55:43Z)
• Low-degree learning and the metric entropy of polynomials [44.99833362998488]
  We prove that any (deterministic or randomized) algorithm which learns $mathscrF_nd$ with $L$-accuracy $varepsilon$ requires at least $Omega(sqrtvarepsilon)2dlog n leq log mathsfM(mathscrF_n,d,|cdot|_L,varepsilon) satisfies the two-sided estimate $$c (1-varepsilon)2dlog
  arXiv  Detail & Related papers  (2022-03-17T23:52:08Z)
• Threshold Phenomena in Learning Halfspaces with Massart Noise [56.01192577666607]
  We study the problem of PAC learning halfspaces on $mathbbRd$ with Massart noise under Gaussian marginals. Our results qualitatively characterize the complexity of learning halfspaces in the Massart model.
  arXiv  Detail & Related papers  (2021-08-19T16:16:48Z)
• On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems [86.92205445270427]
  We consider non-con minimax problems, $min_mathbfx max_mathhidoty f(mathbfdoty)$ efficiently.
  arXiv  Detail & Related papers  (2019-06-02T03:03:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.