Architecture agnostic algorithm for reconfigurable optical interferometer programming

TL;DR

This paper introduces a learning-based algorithm for programming reconfigurable optical interferometers that is architecture agnostic, enabling efficient tuning without requiring explicit analytical models.

Contribution

The authors develop a supervised learning algorithm that can tune optical interferometers to perform desired unitary transformations without relying on analytical decomposition.

Findings

The algorithm successfully matches the interferometer's model to training data.

It can determine phase shifts for desired unitaries even without analytical formulas.

The method facilitates exploration of new interferometric architectures.

Abstract

We develop the learning algorithm to build the architecture agnostic model of the reconfigurable optical interferometer. Programming the unitary transformation on the optical modes of the interferometer either follows the analytical expression yielding the unitary matrix given the set of phaseshifts or requires the optimization routine if the analytic decomposition does not exist. Our algorithm adopts the supervised learning strategy which matches the model of the interferometer to the training set populated by the samples produced by the device under study. The simple optimization routine uses the trained model to output the phaseshifts of the interferometer with the given architecture corresponding to the desired unitary transformation. Our result provides the recipe for efficient tuning of the interferometers even without rigorous analytical description which opens opportunity to explore new architectures of the interferometric circuits.