Information-theoretic generalization bounds for learning from quantum data
- URL: http://arxiv.org/abs/2311.05529v2
- Date: Tue, 18 Jun 2024 18:47:54 GMT
- Title: Information-theoretic generalization bounds for learning from quantum data
- Authors: Matthias Caro, Tom Gur, Cambyse Rouzé, Daniel Stilck França, Sathyawageeswar Subramanian,
- Abstract summary: We propose a general mathematical formalism for describing quantum learning by training on classical-quantum data.
We prove bounds on the expected generalization error of a quantum learner in terms of classical and quantum information-theoretic quantities.
Our work lays a foundation for a unifying quantum information-theoretic perspective on quantum learning.
- Score: 5.0739329301140845
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning tasks play an increasingly prominent role in quantum information and computation. They range from fundamental problems such as state discrimination and metrology over the framework of quantum probably approximately correct (PAC) learning, to the recently proposed shadow variants of state tomography. However, the many directions of quantum learning theory have so far evolved separately. We propose a general mathematical formalism for describing quantum learning by training on classical-quantum data and then testing how well the learned hypothesis generalizes to new data. In this framework, we prove bounds on the expected generalization error of a quantum learner in terms of classical and quantum information-theoretic quantities measuring how strongly the learner's hypothesis depends on the specific data seen during training. To achieve this, we use tools from quantum optimal transport and quantum concentration inequalities to establish non-commutative versions of decoupling lemmas that underlie recent information-theoretic generalization bounds for classical machine learning. Our framework encompasses and gives intuitively accessible generalization bounds for a variety of quantum learning scenarios such as quantum state discrimination, PAC learning quantum states, quantum parameter estimation, and quantumly PAC learning classical functions. Thereby, our work lays a foundation for a unifying quantum information-theoretic perspective on quantum learning.
Related papers
- Separable Power of Classical and Quantum Learning Protocols Through the Lens of No-Free-Lunch Theorem [70.42372213666553]
The No-Free-Lunch (NFL) theorem quantifies problem- and data-independent generalization errors regardless of the optimization process.
We categorize a diverse array of quantum learning algorithms into three learning protocols designed for learning quantum dynamics under a specified observable.
Our derived NFL theorems demonstrate quadratic reductions in sample complexity across CLC-LPs, ReQu-LPs, and Qu-LPs.
We attribute this performance discrepancy to the unique capacity of quantum-related learning protocols to indirectly utilize information concerning the global phases of non-orthogonal quantum states.
arXiv Detail & Related papers (2024-05-12T09:05:13Z) - Quantum algorithms: A survey of applications and end-to-end complexities [90.05272647148196]
The anticipated applications of quantum computers span across science and industry.
We present a survey of several potential application areas of quantum algorithms.
We outline the challenges and opportunities in each area in an "end-to-end" fashion.
arXiv Detail & Related papers (2023-10-04T17:53:55Z) - Statistical Complexity of Quantum Learning [32.48879688084909]
This article reviews the complexity of quantum learning using information-theoretic techniques.
We focus on data complexity, copy complexity, and model complexity.
We highlight the differences between quantum and classical learning by addressing both supervised and unsupervised learning.
arXiv Detail & Related papers (2023-09-20T20:04:05Z) - Quantum data learning for quantum simulations in high-energy physics [55.41644538483948]
We explore the applicability of quantum-data learning to practical problems in high-energy physics.
We make use of ansatz based on quantum convolutional neural networks and numerically show that it is capable of recognizing quantum phases of ground states.
The observation of non-trivial learning properties demonstrated in these benchmarks will motivate further exploration of the quantum-data learning architecture in high-energy physics.
arXiv Detail & Related papers (2023-06-29T18:00:01Z) - Exponential separations between classical and quantum learners [0.0]
We discuss how subtle differences in definitions can result in significantly different requirements and tasks for the learner to meet and solve.
We present two new learning separations where the classical difficulty primarily lies in identifying the function generating the data.
arXiv Detail & Related papers (2023-06-28T08:55:56Z) - Quantum Machine Learning: from physics to software engineering [58.720142291102135]
We show how classical machine learning approach can help improve the facilities of quantum computers.
We discuss how quantum algorithms and quantum computers may be useful for solving classical machine learning tasks.
arXiv Detail & Related papers (2023-01-04T23:37:45Z) - Theory of Quantum Generative Learning Models with Maximum Mean
Discrepancy [67.02951777522547]
We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs)
We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution.
Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
arXiv Detail & Related papers (2022-05-10T08:05:59Z) - Probably approximately correct quantum source coding [0.0]
Holevo's and Nayak's bounds give an estimate of the amount of classical information that can be stored in a quantum state.
We show two novel applications in quantum learning theory and delegated quantum computation with a purely classical client.
arXiv Detail & Related papers (2021-12-13T17:57:30Z) - A Theoretical Framework for Learning from Quantum Data [15.828697880068704]
We propose a theoretical foundation for learning classical patterns from quantum data.
We present a quantum counterpart of the well-known PAC framework.
We establish upper bounds on the quantum sample complexity quantum concept classes.
arXiv Detail & Related papers (2021-07-13T21:39:47Z) - Quantum information spreading in a disordered quantum walk [50.591267188664666]
We design a quantum probing protocol using Quantum Walks to investigate the Quantum Information spreading pattern.
We focus on the coherent static and dynamic disorder to investigate anomalous and classical transport.
Our results show that a Quantum Walk can be considered as a readout device of information about defects and perturbations occurring in complex networks.
arXiv Detail & Related papers (2020-10-20T20:03:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.