Sample complexity of learning fermionic and bosonic Gaussian states with single-copy and entangled measurements
Ron Rubin
Abstract
With single-copy measurements, every mixed fermionic Gaussian state on m modes, pure modes included, is learned to trace distance ε from Θ(m3/ε2) copies, with no logarithmic factor, against the known Θ(m2/ε2) for collective measurements. We prove the upper bound, resolving Conjecture 10.1 of arXiv:2609.23189 (lower bound for ε1/3600), and fill most open entries of the sample-complexity table of fermionic and bosonic Gaussian states, for single-copy, k-copy and collective measurements. With blocks of k copies, the covariant highest-weight measurement of arXiv:2611.07271, read out through the Weyl-shift estimator, is exactly unbiased for every state; it gives Θ(\m3/k,m2\/ε2) in Frobenius norm on all states and in trace distance on every class at a fixed distance from the pure boundary. The gain 1/k (k m) away from the pure boundary, against 1/ k on cold number-conserving states, is therefore attained. Learning a quadratic fermionic Hamiltonian in Frobenius norm from its Gibbs state at bounded β\|h\| has the same rate. For bosonic Gaussian states with bounded covariance, any displacement and squeezing, and occupations n1… nm, O((m2+r3+Σi,j>r1/(ni+nj))/ε2) single-copy measurements suffice, r the largest index with r\,nr2; this is the minimax rate on dyadic-interval classes, with no spectral gap or cold-mode count assumed, and holds with no covariance bound for displaced passive states. With no bound on energy or squeezing, non-Gaussian measurements learn centred one-mode states, mixed included, from O(ε-2) and centred pure m-mode states from O(m2/ε2) single copies, free of the E term of Gaussian measurements, and m-mode states from O(m3/ε2) copies, entangled only in a first round on blocks of 4m+6.
Create a lesson
Related papers
High-temperature Gibbs states are uniformly Markovian and trivial
Andrew D. Kim, Tai Hsuan Yang, Jong Yeon Lee
Query-Optimal Quantum Minimum Finding from Numerical Estimators
Egil Bae
Fast, in-place, and ancilla-free quantum algorithms for integer multiplication and inversion
David Halpenny, Adithya Sireesh, Petros Wallden
High-Accuracy Neural-Network Quantum States via Randomized Real-Time Dynamics
John M. Martyn, Rod Rofougaran, Samuel Stein et al.
End-to-End Quantum Algorithm for Differential Equations: Application to Simulating a Biomolecular System
Mohsen Bagherimehrab, Daniyaal Farooqi, Gavin K. Brennen et al.
Classically Trained Quantum Generative Models with Shared Training and Fine Tuning for Quantum Matter
Mario Herrero-Gonzalez, Elham Kashefi, Mina Doosti