Quantum Occam Learning: Sample-Supported Expressibility for Circuit-Based Quantum Learning

• URL: http://arxiv.org/abs/2606.12211v1
• Date: Wed, 10 Jun 2026 15:28:36 GMT
• Title: Quantum Occam Learning: Sample-Supported Expressibility for Circuit-Based Quantum Learning
• Abstract summary: We develop an information-theoretic Occam theory for quantum data generated by finite-size quantum circuits.<n>With $M$ copies, one can learn up to the best $G$-gate approximation error plus a statistical penalty.<n>Our framework turns bounded circuit complexity into a model-selection principle for quantum machine learning.
• Score: 0.3277163122167433
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: A central principle in quantum machine learning is that an ansatz should be expressive enough to represent the quantum data of interest. Yet, the expressibility is statistically meaningful only insofar as it can be learned from finitely many copies of an unknown quantum state. In this work, we develop an information-theoretic Occam theory for quantum data generated by finite-size quantum circuits. For the class $S_{n,G}$ of $n$-qubit pure states preparable with at most $G$ two-qubit gates, a metric-entropy argument gives the realizable sample law $\widetildeΘ(G/ε^2)$ in the circuit-limited regime. For an arbitrary source $\hatρ$, we introduce the best $G$-gate approximation error $d_G(\hatρ)$ and the approximate circuit complexity $C_η(\hatρ)$. We prove an agnostic quantum Occam theorem: with $M$ copies, one can learn up to the best $G$-gate approximation error plus a statistical penalty $\widetilde{O}(\sqrt{G/M})$. We then remove the need to know $G$ in advance through an adaptive model-selection theorem whose oracle inequality selects the circuit complexity justified by the data. Matching lower bounds yield a sample-supported expressibility law: at trace-distance accuracy $ε$, $M$ samples can support only $G_{\rm supported} \simeq Mε^2$ gates, up to logarithmic factors and tomography saturation at $2^n$. Thus, the circuit complexity becomes an adaptive statistical resource rather than a static promise. Our framework turns bounded circuit complexity into a model-selection principle for quantum machine learning.

Related papers

• Optimal Lower Bounds for Hamiltonian Simulation [42.227880669333835]
  For Hamiltonian $H = sum_j h_j$, we proveally tight lower bounds on the gate and query complexities of simulating time evolution on a quantum computer.<n>Our hold for arbitrary term norms $|h_j|$, time $t$, and trace-distance error $$.
  arXiv  Detail & Related papers  (2026-07-22T07:41:32Z)
• Quantum memory advantage for quantum process tomography [2.956729394666618]
  Quantum process tomography, the task of learning an unknown quantum channel from black-box access, is a central problem in quantum information.<n>We show that quantum memory provides a query-complexity advantage even when protocols without quantum memory may adapt their experiments.<n>Our results establish a rigorous learning separation between quantum process tomography with and without quantum memory.
  arXiv  Detail & Related papers  (2026-07-15T06:09:08Z)
• Adiabatic Quantum Phase Estimation [47.3103723337301]
  Quantum phase estimation (QPE) is a central algorithmic primitive that estimates eigenvalues of a Hamiltonian up to precision $$ in Heisenberg-limited time $T= (1/)$.<n>Standard gate-based implementations of QPE require deep controlled time-evolution circuits and are not native to analog hardware.<n>We present a simple adiabatic protocol for QPE that achieves the optimal Heisenberg-limited scaling $T = Oleft( frac1 logleft(-1right)right)$ in both the precision $$
  arXiv  Detail & Related papers  (2026-05-21T17:31:36Z)
• Quantum channel tomography: optimal bounds and a Heisenberg-to-classical phase transition [29.68432646391692]
  Quantum channel tomography is a fundamental task in the characterization and validation of quantum hardware.<n>Despite extensive prior work, the optimal query complexity for quantum channel tomography is far from fully understood.<n>We show that in the near-boundary regime, the query complexity exhibits a mixture of Heisenberg and classical scaling behaviors.
  arXiv  Detail & Related papers  (2026-04-19T10:51:10Z)
• Shallow quantum circuit for generating O(1)-entangled approximate state designs [6.161617062225404]
  We find a new ensemble of quantum states that serve as an $epsilon$-approximate state $t$-design while possessing extremely low entanglement, magic, and coherence.<n>These resources can reach their theoretical lower bounds, $Omega(log (t/epsilon))$, which are also proven in this work.<n>A class of quantum circuits proposed in our work offers reduced cost for classical simulation of random quantum states.
  arXiv  Detail & Related papers  (2025-07-23T18:56:19Z)
• Nearly Optimal Circuit Size for Sparse Quantum State Preparation [0.0]
  A quantum state is said to be $d$-sparse if it has only $d$ non-zero amplitudes.<n>We prove for the first time a trade-off between the number of ancillary qubits and the circuit size.
  arXiv  Detail & Related papers  (2024-06-23T15:28:20Z)
• Quantum State Learning Implies Circuit Lower Bounds [1.5420873135976756]
  We establish connections between state tomography, pseudorandomness, quantum state, circuit lower bounds.<n>We show that even slightly non-trivial quantum state tomography algorithms would lead to new statements about quantum state synthesis.
  arXiv  Detail & Related papers  (2024-05-16T16:46:27Z)
• Calculating response functions of coupled oscillators using quantum phase estimation [40.31060267062305]
  We study the problem of estimating frequency response functions of systems of coupled, classical harmonic oscillators using a quantum computer.<n>Our proposed quantum algorithm operates in the standard $s-sparse, oracle-based query access model.<n>We show that a simple adaptation of our algorithm solves the random glued-trees problem in time.
  arXiv  Detail & Related papers  (2024-05-14T15:28:37Z)
• Time-Efficient Quantum Entropy Estimator via Samplizer [7.319050391449301]
  Estimating the entropy of a quantum state is a basic problem in quantum information. We introduce a time-efficient quantum approach to estimating the von Neumann entropy $S(rho)$ and R'enyi entropy $S_alpha(rho)$ of an $N$-dimensional quantum state $rho.
  arXiv  Detail & Related papers  (2024-01-18T12:50:20Z)
• On the average-case complexity of learning output distributions of quantum circuits [33.76498647184212]
  We show that learning the output distributions of brickwork random quantum circuits is average-case hard in the statistical query model.<n>This learning model is widely used as an abstract computational model for most generic learning algorithms.
  arXiv  Detail & Related papers  (2023-05-09T20:53:27Z)
• Quantum Resources Required to Block-Encode a Matrix of Classical Data [56.508135743727934]
  We provide circuit-level implementations and resource estimates for several methods of block-encoding a dense $Ntimes N$ matrix of classical data to precision $epsilon$. We examine resource tradeoffs between the different approaches and explore implementations of two separate models of quantum random access memory (QRAM) Our results go beyond simple query complexity and provide a clear picture into the resource costs when large amounts of classical data are assumed to be accessible to quantum algorithms.
  arXiv  Detail & Related papers  (2022-06-07T18:00:01Z)
• On quantum algorithms for the Schr\"odinger equation in the semi-classical regime [27.175719898694073]
  We consider Schr"odinger's equation in the semi-classical regime. Such a Schr"odinger equation finds many applications, including in Born-Oppenheimer molecular dynamics and Ehrenfest dynamics.
  arXiv  Detail & Related papers  (2021-12-25T20:01:54Z)
• Speeding up Learning Quantum States through Group Equivariant Convolutional Quantum Ans\"atze [13.651587339535961]
  We develop a framework for convolutional quantum circuits with SU$(d)$symmetry. We prove Harrow's statement on equivalence between $nameSU(d)$ and $S_n$ irrep bases.
  arXiv  Detail & Related papers  (2021-12-14T18:03:43Z)
• Quantum double aspects of surface code models [77.34726150561087]
  We revisit the Kitaev model for fault tolerant quantum computing on a square lattice with underlying quantum double $D(G)$ symmetry. We show how our constructions generalise to $D(H)$ models based on a finite-dimensional Hopf algebra $H$.
  arXiv  Detail & Related papers  (2021-06-25T17:03:38Z)
• Quantum Coupon Collector [62.58209964224025]
  We study how efficiently a $k$-element set $Ssubseteq[n]$ can be learned from a uniform superposition $|Srangle of its elements. We give tight bounds on the number of quantum samples needed for every $k$ and $n$, and we give efficient quantum learning algorithms.
  arXiv  Detail & Related papers  (2020-02-18T16:14:55Z)

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.