DeepAI AI Chat
Log In Sign Up

A learning theory for quantum photonic processors and beyond

by   Matteo Rosati, et al.

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 establish 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.


page 1

page 2

page 3

page 4


Pseudo-dimension of quantum circuits

We characterize the expressive power of quantum circuits with the pseudo...

Quantum circuits with classical channels and the principle of deferred measurements

We define syntax and semantics of quantum circuits, allowing measurement...

Energy-dependent barren plateau in bosonic variational quantum circuits

Bosonic continuous-variable Variational quantum circuits (VQCs) are cruc...

Clifford Circuits can be Properly PAC Learned if and only if =

Given a dataset of input states, measurements, and probabilities, is it ...

Simple Complete Equational Theories for Quantum Circuits with Ancillae or Partial Trace

Although quantum circuits have been ubiquitous for decades in quantum co...

Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning

With the rapid development of artificial intelligence and autonomous dri...

Symbolic Reasoning about Quantum Circuits in Coq

A quantum circuit is a computational unit that transforms an input quant...