Dimension-Free Polylogarithmic Quantum Shadow Tomography from Sequential Pretty-Good Measurements

• URL: http://arxiv.org/abs/2608.06345v1
• Date: Thu, 06 Aug 2026 17:51:13 GMT
• Title: Dimension-Free Polylogarithmic Quantum Shadow Tomography from Sequential Pretty-Good Measurements
• Abstract summary: We give a quantum protocol for shadow tomography with sample complexity.<n>Our approach first reduces the general shadow-tomography problem to a finite-ensemble estimation problem.<n>A refined tail analysis of the resulting estimation error yields simultaneous accuracy guarantees for all observables.
• Score: 42.01011095596403
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: \textit{Shadow tomography} is a fundamental problem in quantum information theory. Given multiple copies of an unknown $d$-dimensional quantum state $ρ$ and a known collection of observables ${E_1,\ldots,E_m}$, the goal is to estimate all expectation values $\{\Tr(ρE_i)\}_{i=1}^m$ to additive accuracy $\varepsilon$ with probability at least $1-δ$. An elusive open question from the seminal shadow tomography work of Aaronson (STOC'18) is whether this task admits a dimension-independent sample complexity with only polylogarithmic dependence on $m$, as suggested by the best-known lower bounds. In this work, we give a quantum protocol for shadow tomography with sample complexity \[ O\left( \frac{1}{\varepsilon^2} \frac{(\log (m/δ))^4} {(\log\log (m/δ))^3} \right), \] which is polylogarithmic in the number of observables and independent of the dimension of the unknown state thereby answering Aaronson's original question while also providing an exponential improvement in the prior best dimension independent sample complexity of shadow tomography from Sinha (STOC'25). Our approach first reduces the general shadow-tomography problem to a finite-ensemble estimation problem via a minimax argument. We then develop an observable-independent protocol that repeatedly applies the pretty-good measurement and updates the priori distribution over the finite ensemble according to the measurement outcomes. A refined tail analysis of the resulting estimation error yields simultaneous accuracy guarantees for all observables.

Related papers

• The log log jam in Gaussian state tomography [30.395638404311537]
  We show that any protocol that uses Gaussian measurements, even entangled or adaptively chosen ones, must incur a $log log E$ dependence.<n>With highly entangled, non-Gaussian measurements, one can learn $n$-mode pure Gaussian states with $O(n2 / 2)$ samples, independent of $E$.<n>Our results shed new light on the intriguing interplay between adaptivity, entanglement, and magic in quantum learning.
  arXiv  Detail & Related papers  (2026-07-14T17:25:43Z)
• Efficient Shadow Tomography of Thermal States [0.5500249707065662]
  We present a general protocol for estimating $M$ observables from only $mathcalO(log (M)/varepsilon2)$ copies of a Gibbs state whose Hamiltonian is accessible.<n>We show that the sample complexity is optimal in a black-box setting where exponential time Hamiltonian simulation is prohibited.
  arXiv  Detail & Related papers  (2026-03-17T17:53:12Z)
• Instance-optimal high-precision shadow tomography with few-copy measurements: A metrological approach [2.956729394666618]
  We study the sample complexity of shadow tomography in the high-precision regime.<n>We use possibly adaptive measurements that act on $O(mathrmpolylog(d))$ number of copies of $$ at a time.
  arXiv  Detail & Related papers  (2026-02-04T19:00:00Z)
• Beyond likelihood ratio bias: Nested multi-time-scale stochastic approximation for likelihood-free parameter estimation [49.78792404811239]
  We study inference in simulation-based models where the analytical form of the likelihood is unknown.<n>We use a ratio-free nested multi-time-scale approximation (SA) method that simultaneously tracks the score and drives the parameter update.<n>We show that our algorithm can eliminate the original bias $Obig(sqrtfrac1Nbig)$ and accelerate the convergence rate from $Obig(beta_k+sqrtfracalpha_kNbig)$.
  arXiv  Detail & Related papers  (2024-11-20T02:46:15Z)
• Dimension-free Private Mean Estimation for Anisotropic Distributions [55.86374912608193]
  Previous private estimators on distributions over $mathRd suffer from a curse of dimensionality. We present an algorithm whose sample complexity has improved dependence on dimension.
  arXiv  Detail & Related papers  (2024-11-01T17:59:53Z)
• Data subsampling for Poisson regression with pth-root-link [53.63838219437508]
  We develop and analyze data subsampling techniques for Poisson regression. In particular, we consider the Poisson generalized linear model with ID- and square root-link functions.
  arXiv  Detail & Related papers  (2024-10-30T10:09:05Z)
• Resource-efficient shadow tomography using equatorial stabilizer measurements [0.0]
  We propose a resource-efficient shadow-tomography scheme using equatorial-stabilizer measurements generated from subsets of Clifford unitaries.<n>For $n$-qubit systems, equatorial-stabilizer-based shadow-tomography schemes can estimate $M$ observables (up to an additive error $varepsilon$) using $mathcalO(log(M),mathrmpoly(n),1/varepsilon2)$ sampling copies.<n>We numerically confirm our theoretically-derived shadow-tomographic sampling complexities with random pure states and multiqubit graph
  arXiv  Detail & Related papers  (2023-11-24T17:33:44Z)
• Lower Bounds for Learning Quantum States with Single-Copy Measurements [2.7869568828212175]
  We study the problems of quantum tomography and shadow tomography using measurements performed on individual copies of an unknown $d$-dimensional state.<n>In particular, this rigorously establishes the optimality of the folklore Pauli tomography" algorithm in terms of its complexity.
  arXiv  Detail & Related papers  (2022-07-29T02:26:08Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)
• Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model [50.38446482252857]
  This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator) We first consider $gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space $mathcalS$ and action space $mathcalA$. We prove that a plain model-based planning algorithm suffices to achieve minimax-optimal sample complexity given any target accuracy level.
  arXiv  Detail & Related papers  (2020-05-26T17:53:18Z)

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.