Quantum Chebyshev Transform: Mapping, Embedding, Learning and Sampling Distributions

TL;DR

This paper introduces a quantum Chebyshev transform framework that encodes data into quantum states using Chebyshev polynomials, enabling efficient modeling, differentiation, and sampling of complex distributions.

Contribution

It presents a novel quantum circuit for mapping between computational and Chebyshev spaces, facilitating advanced quantum modeling and sampling techniques.

Findings

Efficient encoding of data into quantum states with Chebyshev polynomials.

Enabling automatic differentiation in quantum models.

Application to generative modeling and sampling of complex distributions.

Abstract

We develop a paradigm for building quantum models in the orthonormal space of Chebyshev polynomials. We show how to encode data into quantum states with amplitudes being Chebyshev polynomials with degree growing exponentially in the system size. Similar to the quantum Fourier transform which maps computational basis space into the phase (Fourier) basis, we describe the quantum circuit for the mapping between computational and Chebyshev spaces. We propose an embedding circuit for generating the orthonormal Chebyshev basis of exponential capacity, represented by a continuously-parameterized shallow isometry. This enables automatic quantum model differentiation, and opens a route to solving stochastic differential equations. We apply the developed paradigm to generative modeling from physically- and financially-motivated distributions, and use the quantum Chebyshev transform for efficient sampling of these distributions in extended computational basis.