Log In Sign Up

Bandwidth Enables Generalization in Quantum Kernel Models

by   Abdulkadir Canatar, et al.

Quantum computers are known to provide speedups over classical state-of-the-art machine learning methods in some specialized settings. For example, quantum kernel methods have been shown to provide an exponential speedup on a learning version of the discrete logarithm problem. Understanding the generalization of quantum models is essential to realizing similar speedups on problems of practical interest. Recent results demonstrate that generalization is hindered by the exponential size of the quantum feature space. Although these results suggest that quantum models cannot generalize when the number of qubits is large, in this paper we show that these results rely on overly restrictive assumptions. We consider a wider class of models by varying a hyperparameter that we call quantum kernel bandwidth. We analyze the large-qubit limit and provide explicit formulas for the generalization of a quantum model that can be solved in closed form. Specifically, we show that changing the value of the bandwidth can take a model from provably not being able to generalize to any target function to good generalization for well-aligned targets. Our analysis shows how the bandwidth controls the spectrum of the kernel integral operator and thereby the inductive bias of the model. We demonstrate empirically that our theory correctly predicts how varying the bandwidth affects generalization of quantum models on challenging datasets, including those far outside our theoretical assumptions. We discuss the implications of our results for quantum advantage in machine learning.


page 5

page 7

page 12

page 14

page 19

page 20

page 22

page 23


Numerical evidence against advantage with quantum fidelity kernels on classical data

Quantum machine learning techniques are commonly considered one of the m...

Importance of Kernel Bandwidth in Quantum Machine Learning

Quantum kernel methods are considered a promising avenue for applying qu...

The Inductive Bias of Quantum Kernels

It has been hypothesized that quantum computers may lend themselves well...

Generalization in Quantum Machine Learning: a Quantum Information Perspective

We study the machine learning problem of generalization when quantum ope...

Quantum Kerr Learning

Quantum machine learning is a rapidly evolving area that could facilitat...

A kernel-based quantum random forest for improved classification

The emergence of Quantum Machine Learning (QML) to enhance traditional c...

How Much Structure Is Needed for Huge Quantum Speedups?

I survey, for a general scientific audience, three decades of research i...