Efficient learning of bosonic unitaries beyond the Gaussian class

• URL: http://arxiv.org/abs/2607.27534v1
• Date: Thu, 30 Jul 2026 00:03:07 GMT
• Title: Efficient learning of bosonic unitaries beyond the Gaussian class
• Abstract summary: Multimode quantum processes are generally difficult to learn.<n>We show that the fundamental obstruction is not non-Gaussianity itself, but the buildup of irreducible multimode non-Gaussian correlations.
• Score: 1.9157770789584179
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Multimode quantum processes are generally difficult to learn, due to the large dimensionality and complex entanglement structure beyond the Gaussian class. Here, we show that the fundamental obstruction is not non-Gaussianity itself, but the buildup of irreducible multimode non-Gaussian correlations. We establish a tractability frontier for bosonic unitary learning: a general $m$-mode unitary with input energy at most $E$ per mode requires at least $Ω(E^{2m})$ channel uses, whereas two broad non-Gaussian families---$t$-doped Gaussian unitaries and Gaussian-entanglable unitaries---can be learned with resources polynomial in $m$. The latter can exhibit both extensive non-Gaussianity and strong multimode entanglement. Our forward-only protocols use coherent-state probes, Gaussian operations, local heterodyne detection, and classical post-processing to identify the global Gaussian mixing and reduce the remaining task to single- or few-mode learning. The analysis also yields a multimode quantum Darmois--Skitovich theorem showing that mode-spreading passive networks preserve product structure only for Gaussian input states, an almost-sure activation theorem for non-Gaussian processes showing that non-Gaussian unitaries yield non-Gaussian outputs for almost all coherent input states, and a method for learning unitaries from uncalibrated coherent probes. Our results identify that complexity of learning arises from irreducible mixing of non-Gaussianity and entanglement, rather than either resource alone.

Related papers

• Fermionic non-Gaussianity via Bell sampling: monotones and efficient quantum algorithms [0.0]
  We develop efficient quantum algorithms for fermionic non-Gaussianity, all built on the eigenvalue structure of the operator $= sum_j=12n_jotimes_j.<n>We introduce the emphbridge degree of even pure states, a novel non-Gaussianity monotone defined as the largest eigenvalue sector of $$ populated by two copies of the state.
  arXiv  Detail & Related papers  (2026-06-03T16:29:05Z)
• Non-Gaussian Entanglement Hierarchy Based on the Schmidt Number [2.999888908665658]
  Non-Gaussian entanglement is a promising resource in various quantum tasks.<n>We introduce a quantitative witness $E_rm NG$ in bipartite bosonic systems.<n>We benchmark the framework with some paradigmatic non-Gaussian states, such as NOON states and squeezed Kerr states.
  arXiv  Detail & Related papers  (2026-05-18T16:15:17Z)
• Towards sample-optimal learning of bosonic Gaussian quantum states [7.657727267684591]
  A fundamental question is how to characterize an unknown bosonic Gaussian state from as few samples as possible.<n>We study the necessary and sufficient number of copies to learn an $n$-mode Gaussian state, with energy less than $E$, to $varepsilon$ trace distance with high probability.<n>Our results greatly advance quantum learning theory in the bosonic regimes and have practical impact in quantum sensing and benchmarking applications.
  arXiv  Detail & Related papers  (2026-03-18T18:00:00Z)
• Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures [53.51230405648361]
  We study the dynamics of gradient EM and employ tensor decomposition to characterize the geometric landscape of the likelihood loss.<n>This is the first global convergence and recovery result for EM or gradient EM beyond the special case of $m=2$.
  arXiv  Detail & Related papers  (2025-06-06T23:32:38Z)
• The Generative Leap: Sharp Sample Complexity for Efficiently Learning Gaussian Multi-Index Models [71.5283441529015]
  In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) $d$-dimensional inputs through their projection onto a low-dimensional $r = O_d(1)$ subspace.<n>We introduce the generative leap exponent $kstar$, a natural extension of the generative exponent from [Damian et al.'24] to the multi-index setting.
  arXiv  Detail & Related papers  (2025-06-05T18:34:56Z)
• The symplectic rank of non-Gaussian quantum states [0.0]
  Non-Gaussianity is a key resource for achieving quantum advantages in bosonic platforms.<n>Here, we investigate the symplectic rank: a novel non-Gaussianity monotone that satisfies remarkable operational and resource-theoretic properties.<n>We show that the symplectic rank is a robust non-Gaussian measure, explaining how to witness it in experiments and how to exploit it to meaningfully benchmark different bosonic platforms.
  arXiv  Detail & Related papers  (2025-04-27T18:00:31Z)
• Learning Mixtures of Gaussians Using Diffusion Models [9.118706387430883]
  We give a new algorithm for learning mixtures of $k$ Gaussians to TV error $varepsilon$, with quasi-polynomial ($O(ntextpoly,logleft(fracn+kvarepsilonright))$) time and sample complexity.<n>Results extend to continuous mixtures of Gaussians where the mixing distribution is supported on a union of $k$ balls of constant radius.
  arXiv  Detail & Related papers  (2024-04-29T17:00:20Z)
• A single $T$-gate makes distribution learning hard [56.045224655472865]
  This work provides an extensive characterization of the learnability of the output distributions of local quantum circuits. We show that for a wide variety of the most practically relevant learning algorithms -- including hybrid-quantum classical algorithms -- even the generative modelling problem associated with depth $d=omega(log(n))$ Clifford circuits is hard.
  arXiv  Detail & Related papers  (2022-07-07T08:04:15Z)
• Deterministic Gaussian conversion protocols for non-Gaussian single-mode resources [58.720142291102135]
  We show that cat and binomial states are approximately equivalent for finite energy, while this equivalence was previously known only in the infinite-energy limit. We also consider the generation of cat states from photon-added and photon-subtracted squeezed states, improving over known schemes by introducing additional squeezing operations.
  arXiv  Detail & Related papers  (2022-04-07T11:49:54Z)
• Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
  We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
  arXiv  Detail & Related papers  (2020-11-18T16:40:45Z)
• Learning Halfspaces with Tsybakov Noise [50.659479930171585]
  We study the learnability of halfspaces in the presence of Tsybakov noise. We give an algorithm that achieves misclassification error $epsilon$ with respect to the true halfspace.
  arXiv  Detail & Related papers  (2020-06-11T14:25:02Z)

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.