On the Computational Power of QAC0 with Barely Superlinear Ancillae

• URL: http://arxiv.org/abs/2410.06499v2
• Date: Thu, 31 Oct 2024 02:46:04 GMT
• Title: On the Computational Power of QAC0 with Barely Superlinear Ancillae
• Authors: Anurag Anshu, Yangjing Dong, Fengning Ou, Penghui Yao,
• Abstract summary: We show that any depth-$d$ $mathrmQAC0$ circuit requires $n1+3-d$ ancillae to compute a function with approximate degree $ta(n)$. This is the first superlinear lower bound on the super-linear sized $mathrmQAC0$.
• Score: 10.737102385599169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: $\mathrm{QAC}^0$ is the family of constant-depth polynomial-size quantum circuits consisting of arbitrary single qubit unitaries and multi-qubit Toffoli gates. It was introduced by Moore [arXiv: 9903046] as a quantum counterpart of $\mathrm{AC}^0$, along with the conjecture that $\mathrm{QAC}^0$ circuits can not compute PARITY. In this work we make progress on this longstanding conjecture: we show that any depth-$d$ $\mathrm{QAC}^0$ circuit requires $n^{1+3^{-d}}$ ancillae to compute a function with approximate degree $\Theta(n)$, which includes PARITY, MAJORITY and $\mathrm{MOD}_k$. We further establish superlinear lower bounds on quantum state synthesis and quantum channel synthesis. This is the first superlinear lower bound on the super-linear sized $\mathrm{QAC}^0$. Regarding PARITY, we show that any further improvement on the size of ancillae to $n^{1+\exp(-o(d))}$ would imply that PARITY $\not\in$ QAC0. These lower bounds are derived by giving low-degree approximations to $\mathrm{QAC}^0$ circuits. We show that a depth-$d$ $\mathrm{QAC}^0$ circuit with $a$ ancillae, when applied to low-degree operators, has a degree $(n+a)^{1-3^{-d}}$ polynomial approximation in the spectral norm. This implies that the class $\mathrm{QLC}^0$, corresponding to linear size $\mathrm{QAC}^0$ circuits, has approximate degree $o(n)$. This is a quantum generalization of the result that $\mathrm{LC}^0$ circuits have approximate degree $o(n)$ by Bun, Robin, and Thaler [SODA 2019]. Our result also implies that $\mathrm{QLC}^0\neq\mathrm{NC}^1$.

Related papers

• 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)
• Unconditionally separating noisy $\mathsf{QNC}^0$ from bounded polynomial threshold circuits of constant depth [8.66267734067296]
  We study classes of constant-depth circuits with bounds that compute restricted threshold functions. For large enough values of $mathsfbPTFC0[k]$, $mathsfbPTFC0[k] contains $mathsfTC0[k].
  arXiv  Detail & Related papers  (2024-08-29T09:40:55Z)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit [75.4661041626338]
  We study the problem of gradient descent learning of a single-index target function $f_*(boldsymbolx) = textstylesigma_*left(langleboldsymbolx,boldsymbolthetarangleright)$ under isotropic Gaussian data. We prove that a two-layer neural network optimized by an SGD-based algorithm learns $f_*$ of arbitrary link function with a sample and runtime complexity of $n asymp T asymp C(q) cdot d
  arXiv  Detail & Related papers  (2024-06-03T17:56:58Z)
• 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)
• Parity vs. AC0 with simple quantum preprocessing [0.0]
  We study a hybrid circuit model where $mathsfAC0$ operates on measurement outcomes of a $mathsfQNC0$ circuit. We find that while $mathsfQNC0$ is surprisingly powerful for search and sampling tasks, that power is "locked away" in the global correlations of its output.
  arXiv  Detail & Related papers  (2023-11-22T20:27:05Z)
• 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)
• The Approximate Degree of DNF and CNF Formulas [95.94432031144716]
  For every $delta>0,$ we construct CNF and formulas of size with approximate degree $Omega(n1-delta),$ essentially matching the trivial upper bound of $n. We show that for every $delta>0$, these models require $Omega(n1-delta)$, $Omega(n/4kk2)1-delta$, and $Omega(n/4kk2)1-delta$, respectively.
  arXiv  Detail & Related papers  (2022-09-04T10:01:39Z)
• 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)
• 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)
• Bounds on the QAC$^0$ Complexity of Approximating Parity [0.0]
  We prove that QAC circuits of sublogarithmic depth can approximate parity regardless of size. QAC circuits require at least $Omega(n/d)$ multi-qubit gates to achieve a $1/2 + exp(-o(n/d))$ approximation of parity.
  arXiv  Detail & Related papers  (2020-08-17T16:51:04Z)

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.