Quantum Mean Embedding of Probability Distributions

Abstract

The kernel mean embedding of probability distributions is commonly used in machine learning as an injective mapping from distributions to functions in an infinite dimensional Hilbert space. It allows us, for example, to define a distance measure between probability distributions, called maximum mean discrepancy (MMD). In this work, we propose to represent probability distributions in a pure quantum state of a system that is described by an infinite dimensional Hilbert space. This enables us to work with an explicit representation of the mean embedding, whereas classically one can only work implicitly with an infinite dimensional Hilbert space through the use of the kernel trick. We show how this explicit representation can speed up methods that rely on inner products of mean embeddings and discuss the theoretical and experimental challenges that need to be solved in order to achieve these speedups.

arXiv comment7 pages, 2 figures

References in corpus (20)

• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• Quantum Coherence as a Resource
• Quantum machine learning in feature Hilbert spaces
• Quantum principal component analysis
• Quantum fingerprinting
• Quantum random access memory
• Reconstruction of non-classical cavity field states with snapshots of their decoherence
• Quantum machine learning: a classical perspective
• Hybrid quantum information processing
• Kernel Mean Embedding of Distributions: A Review and Beyond
• Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks
• Learning the quantum algorithm for state overlap
• A resource theory of superposition
• A device for feasible fidelity, purity, Hilbert-Schmidt distance and entanglement witness measurements
• Creation of superposition of unknown quantum states
• The Forbidden Quantum Adder
• Generalized Coherent States, Reproducing Kernels, and Quantum Support Vector Machines
• Detecting the degree of macroscopic quantumness using an overlap measurement
• Measuring non-linear functionals of quantum harmonic oscillator states

Cited by in corpus (6)

• Robust data encodings for quantum classifiers
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• A Continuous Variable Born Machine
• Ancilla-Error-Transparent Controlled Beam Splitter Gate
• Quantum Kernel Evaluation via Hong-Ou-Mandel Interference
• The Physics of Learning