Classical surrogates for quantum learning models

Abstract

The advent of noisy intermediate-scale quantum computers has put the search for possible applications to the forefront of quantum information science. One area where hopes for an advantage through near-term quantum computers are high is quantum machine learning, where variational quantum learning models based on parametrized quantum circuits are discussed. In this work, we introduce the concept of a classical surrogate, a classical model which can be efficiently obtained from a trained quantum learning model and reproduces its input-output relations. As inference can be performed classically, the existence of a classical surrogate greatly enhances the applicability of a quantum learning strategy. However, the classical surrogate also challenges possible advantages of quantum schemes. As it is possible to directly optimize the ansatz of the classical surrogate, they create a natural benchmark the quantum model has to outperform. We show that large classes of well-analyzed re-uploading models have a classical surrogate. We conducted numerical experiments and found that these quantum models show no advantage in performance or trainability in the problems we analyze. This leaves only generalization capability as possible point of quantum advantage and emphasizes the dire need for a better understanding of inductive biases of quantum learning models.

4 pages, 3 figures

References in corpus (1)

• An introduction to quantum machine learning

Cited by in corpus (29)

• Does provable absence of barren plateaus imply classical simulability?
• Shadows of quantum machine learning
• Quantum Machine Learning for Digital Health? A Systematic Review
• On fundamental aspects of quantum extreme learning machines
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Lie-algebraic classical simulations for quantum computing
• Dequantizing quantum machine learning models using tensor networks
• Potential and limitations of random Fourier features for dequantizing quantum machine learning
• On the expressivity of embedding quantum kernels
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Opportunities and challenges of quantum computing for climate modelling
• Barren plateaus are swamped with traps
• Quantum continual learning on a programmable superconducting processor
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits
• Gradients and frequency profiles of quantum re-uploading models
• Quantum computing for genomics: conceptual challenges and practical perspectives
• Quantum Computing for Data Centric Engineering and Science
• Efficient quantum-enhanced classical simulation for patches of quantum landscapes
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Learning Fourier series with parametrized quantum circuits
• Learning unitaries with quantum statistical queries
• When Quantum and Classical Models Disagree: Learning Beyond Minimum Norm Least Square
• Artificial intelligence for representing and characterizing quantum systems
• Building Continuous Quantum-Classical Bayesian Neural Networks for a Classical Clinical Dataset
• Interpolation-based coordinate descent method for parameterized quantum circuits
• Quantum feature-map learning with reduced resource overhead
• Quantum Machine Learning for Climate Modelling
• New perspectives on quantum kernels through the lens of entangled tensor kernels
• Gradient Scalability and Taylor Surrogation of Quantum Cost Landscapes