A learning theory for quantum photonic processors and beyond
arXiv:2209.03075 · doi:10.22331/q-2024-08-08-1433
Abstract
We consider the tasks of learning quantum states, measurements and channels generated by continuous-variable (CV) quantum circuits. This family of circuits is suited to describe optical quantum technologies and in particular it includes state-of-the-art photonic processors capable of showing quantum advantage. We define classes of functions that map classical variables, encoded into the CV circuit parameters, to outcome probabilities evaluated on those circuits. We then establish efficient learnability guarantees for such classes, by computing bounds on their pseudo-dimension or covering numbers, showing that CV quantum circuits can be learned with a sample complexity that scales polynomially with the circuit's size, i.e., the number of modes. Our results show that CV circuits can be trained efficiently using a number of training samples that, unlike their finite-dimensional counterpart, does not scale with the circuit depth.
arXiv comment27+5 pages, 2 figures
References in corpus (32)
- Quantum computational advantage using photons
- Integrated Photonic Quantum Technologies
- Predicting Many Properties of a Quantum System from Very Few Measurements
- Quantum computation over continuous variables
- Hybrid quantum information processing
- New class of quantum error-correcting codes for a bosonic mode
- Blueprint for a Scalable Photonic Fault-Tolerant Quantum Computer
- Resolving the energy levels of a nanomechanical oscillator
- Fast Universal Control of an Oscillator with Weak Dispersive Coupling to a Qubit
- Universal Control of an Oscillator with Dispersive Coupling to a Qubit
- Multidimensional Hermite polynomials and photon distribution for polymode mixed light
- Encoding an oscillator into many oscillators
- On the Quantum versus Classical Learnability of Discrete Distributions
- Revisiting the Dolinar Receiver through Multiple-Copy State Discrimination Theory
- Reconfigurable continuously-coupled 3D photonic circuit for Boson Sampling experiments
- Measurement-free preparation of grid states
- Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions
- Fast simulation of bosonic qubits via Gaussian functions in phase space
- Classical shadow tomography for continuous variables quantum systems
- Pseudo-dimension of quantum circuits
- Real-time calibration of coherent-state receivers: learning by trial and error
- Achieving the Holevo bound via a bisection decoding protocol
- Linear optics and photodetection achieve near-optimal unambiguous coherent state discrimination
- Optimal quantum state discrimination via nested binary measurements
- Squeezing-enhanced communication without a phase reference
- The capacity of coherent-state adaptive decoders with interferometry and single-mode detectors
- Accessible coherence in open quantum system dynamics
- The Learnability of Quantum States
- Generalized quantum process discrimination problems
- Demonstration of optimal non-projective measurement of binary coherent states with photon counting
- Reinforcement-learning calibration of coherent-state receivers on variable-loss optical channels
- Quantum process discrimination with restricted strategies