Is Quantum Advantage the Right Goal for Quantum Machine Learning? (2022-03-02T00:00:00.000000Z)

TL;DR

It is argued that these challenges call for a critical debate on whether quantum advantage and the narrative of 'beating' classical machine learning should continue to dominate the literature the way it does, and examples for how other perspectives in existing research provide an important alternative to the focus on advantage.

Abstract

Machine learning is frequently listed among the most promising applications for quantum computing. This is in fact a curious choice: Today's machine learning algorithms are notoriously powerful in practice, but remain theoretically difficult to study. Quantum computing, in contrast, does not offer practical benchmarks on realistic scales, and theory is the main tool we have to judge whether it could become relevant for a problem. In this perspective we explain why it is so difficult to say something about the practical power of quantum computers for machine learning with the tools we are currently using. We argue that these challenges call for a critical debate on whether quantum advantage and the narrative of 'beating' classical machine learning should continue to dominate the literature the way it does, and highlight examples for how other perspectives in existing research provide an important alternative to the focus on advantage.

Authors

M. Schuld

7 papers

N. Killoran

4 papers

TL;DR

Abstract

Authors

References129 items

The complexity of quantum support vector machines

Uncovering Instabilities in Variational-Quantum Deep Q-Networks

Quantum machine learning with subspace states

Quantum advantage in learning from experiments

Generalization in quantum machine learning from few training data

Representation Learning via Quantum Neural Tangent Kernels

Quantum tangent kernel

A Case for Noisy Shallow Gate-based Circuits in Quantum Machine Learning

Quantum-classical hybrid neural networks in the neural tangent kernel regime

Entangled Datasets for Quantum Machine Learning

Generalized quantum circuit differentiation rules

General parameter-shift rules for quantum gradients

A quantum algorithm for training wide and deep classical neural networks

Analytic gradients in variational quantum algorithms: Algebraic extensions of the parameter-shift rule to general unitary transformations

The Inductive Bias of Quantum Kernels

Deep learning: a statistical viewpoint

Understanding deep learning (still) requires rethinking generalization

Generalization in Quantum Machine Learning: a Quantum Information Perspective

Structure optimization for parameterized quantum circuits

Quantum machine learning models are kernel methods

Machine learning of high dimensional data on a noisy quantum processor

Expressivity of quantum neural networks

Information-theoretic bounds on quantum advantage in machine learning

Connecting ansatz expressibility to gradient magnitudes and barren plateaus

Anomalous collapses of Nares Strait ice arches leads to enhanced export of Arctic sea ice

Variational quantum algorithms

A feasible approach for automatically differentiable unitary coupled-cluster on quantum computers

Focus beyond Quadratic Speedups for Error-Corrected Quantum Advantage

Power of data in quantum machine learning

The power of quantum neural networks

Quantum Deformed Neural Networks

A rigorous and robust quantum speed-up in supervised machine learning

Effect of data encoding on the expressive power of variational quantum-machine-learning models

Estimating the gradient and higher-order derivatives on quantum hardware

On the Quantum versus Classical Learnability of Discrete Distributions

Expressive power of parametrized quantum circuits

Measuring Analytic Gradients of General Quantum Evolution with the Stochastic Parameter Shift Rule

Operator Sampling for Shot-frugal Optimization in Variational Algorithms

A non-review of Quantum Machine Learning: trends and explorations

Quantum embeddings for machine learning

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Continuous variable quantum perceptron

An Adaptive Optimizer for Measurement-Frugal Variational Algorithms

Quantum Natural Gradient

Data re-uploading for a universal quantum classifier

Benign overfitting in linear regression

Parameterized quantum circuits as machine learning models

Implicit Regularization in Deep Matrix Factorization

Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition

Training deep quantum neural networks

Calculus on parameterized quantum circuits.

Evaluating analytic gradients on quantum hardware

An artificial neuron implemented on an actual quantum processor

Quantum convolutional neural networks

Framework

A quantum-inspired classical algorithm for recommendation systems

Neural Tangent Kernel: Convergence and Generalization in Neural Networks

Continuous-variable quantum neural networks

Supervised learning with quantum-enhanced feature spaces

Differentiable Learning of Quantum Circuit Born Machine

Circuit-centric quantum classifiers

Barren plateaus in quantum neural network training landscapes

Quantum Machine Learning in Feature Hilbert Spaces.

Quantum circuit learning

Classification with Quantum Neural Networks on Near Term Processors

Unitary quantum perceptron as efficient universal approximator

Learning relevant features of data with multi-scale tensor networks

Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines

Quantum Neuron: an elementary building block for machine learning on quantum computers

The Implicit Bias of Gradient Descent on Separable Data

Dealing with the positive publication bias: Why you should really publish your negative results

Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers

Quantum machine learning: a classical perspective

Inductive Supervised Quantum Learning.

Open quantum generalisation of Hopfield neural networks

Generalized coherent states, reproducing kernels, and quantum support vector machines