Variational quantum circuit algorithm is suggested as a machine learning paradigm to utilize the power of Noisy Intermediate-Scale Quantum hardware. Recent efforts lead to better theoretical understanding of the expressibility and generalization ability of quantum circuits. In this work, we compare our previous results on the quantum circuit learnability based on VC theory to some preliminary results based on PAC-Bayesian method. Some recent developments based on other generalization bounds due to other research groups are also reviewed and discussed.
Variational quantum circuit algorithm is suggested as a machine learning paradigm to utilize the power of Noisy Intermediate-Scale Quantum hardware. Recent efforts lead to better theoretical understanding of the expressibility and generalization ability of quantum circuits. In this work, we compare our previous results on the quantum circuit learnability based on VC theory to some preliminary results based on PAC-Bayesian method. Some recent developments based on other generalization bounds due to other research groups are also reviewed and discussed.
Applying quantum processors to model a high-dimensional function approximator is a typical method in quantum machine learning with potential advantage. It is conjectured that the unitarity of quantum circuits provides possible regularization to avoid overfitting. However, it is not clear how the regularization interplays with the expressibility under the limitation of current Noisy-Intermediate Scale Quantum devices. In this article, we perform simulations and theoretical analysis of the quantum circuit learning problem with hardware-efficient ansatz. Thorough numerical simulations show that the expressibility and generalization error scaling of the ansatz saturate when the circuit depth increases, implying the automatic regularization to avoid the overfitting issue in the quantum circuit learning scenario. This observation is supported by the theory on PAC learnability, which proves that VC dimension is upper bounded due to the locality and unitarity of the hardware-efficient ansatz. Our study provides supporting evidence for automatic regularization by unitarity to suppress overfitting and guidelines for possible performance improvement under hardware constraints.
Variational Quantum Circuits (VQCs) have emerged as a cornerstone of hybrid quantum–classical algorithms designed to harness the computational potential of near-term quantum devices. By combining parameterized quantum gates with classical optimization, VQCs provide a flexible framework for tackling machine learning, chemistry, and optimization problems intractable for classical methods. This review comprehensively overviews VQC design principles, ansatz structures, optimization strategies, and real-world applications. Furthermore, we discuss fundamental challenges such as barren plateaus, the expressibility–trainability trade-off, and current noisy intermediate-scale quantum (NISQ) hardware limitations. Finally, we highlight emerging directions that could enable scalable, noise-resilient, and physically interpretable variational quantum models for future quantum computing applications
Generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function learned. These capacity-based uniform bounds are often too loose and entirely insensitive to the actual training and learning process. Previous theoretical guarantees have failed to provide non-uniform, data-dependent bounds that reflect the specific properties of the learned solution rather than the worst-case behavior of the entire hypothesis class. To address this limitation, we derive the first PAC-Bayesian generalization bounds for a broad class of quantum models by analyzing layered circuits composed of general quantum channels, which include dissipative operations such as mid-circuit measurements and feedforward. Through a channel perturbation analysis, we establish non-uniform bounds that depend on the norms of learned parameter matrices; we extend these results to symmetry-constrained equivariant quantum models; and we validate our theoretical framework with numerical experiments. This work provides actionable model design insights and establishes a foundational tool for a more nuanced understanding of generalization in quantum machine learning.
Quantum machine learning is increasingly being explored as a way to tackle complex data analysis problems by combining quantum computing with modern learning techniques. In particular, variational quantum classifiers have attracted considerable attention because they can be implemented on current noisy intermediate-scale quantum (NISQ) devices. Despite their potential, most existing variational quantum classifiers rely on deterministic optimization of circuit parameters. Such approaches can struggle when the available training data are limited or noisy, often leading to unstable predictions and reduced reliability. To address these challenges, recent research has begun incorporating Bayesian learning principles into variational quantum models. By treating circuit parameters as probabilistic variables rather than fixed values, Bayesian variational quantum classifiers allow uncertainty to be explicitly modeled during the learning process. This makes it possible to obtain predictions that are not only accurate but also accompanied by meaningful confidence estimates. In this paper, we present a detailed analysis of Bayesian variational quantum classifiers and their role in enabling uncertainty-aware quantum machine learning. The discussion covers the foundations of variational quantum circuits, Bayesian parameter estimation, and probabilistic prediction mechanisms within hybrid quantum-classical learning frameworks. Different training and inference strategies, including variational Bayesian optimization and sampling-based methods, are examined to highlight their effectiveness in capturing parameter uncertainty in quantum circuits. We also discuss emerging application areas, such as healthcare analytics, financial forecasting, and scientific data analysis, where uncertainty-aware quantum learning models can provide valuable insights.
This chapter develops a learning-theoretical foundation for quantum machine learning (QML) by treating quantum models as statistical learning systems rather than merely as computational circuits or algorithms. The discussion begins by motivating the need for learning theory in QML, emphasizing that nominal expressivity in exponentially large Hilbert spaces does not automatically imply learnability or generalization. Classical concepts such as VC dimension and Rademacher complexity are then adapted to quantum settings to analyze the effective capacity of parameterized quantum circuits and quantum kernels. These tools show that accessible quantum hypothesis classes are far more constrained than naive Hilbert-space arguments suggest and that increased expressivity can easily lead to overfitting when not balanced by appropriate inductive bias and regularization. This chapter further examines generalization bounds for variational quantum circuits, highlighting the additional roles of measurement-induced stochasticity, finite-shot variance, and hardware noise. Overfitting, implicit and explicit regularization, and the possibility of double-descent-like behavior in quantum models are analyzed from a unified statistical perspective. A final synthesis shows that expressivity, trainability, and robustness are fundamentally coupled in QML. Hands-on examples in Qiskit and PennyLane illustrate kernel complexity, generalization gaps, and depth-dependent trainability. Overall, this chapter provides a principled framework for evaluating when quantum models can learn reliably from finite, noisy data.
The state-of-the-art machine learning approaches are based on classical von Neumann computing architectures and have been widely used in many industrial and academic domains. With the recent development of quantum computing, researchers and tech-giants have attempted new quantum circuits for machine learning tasks. However, the existing quantum computing platforms are hard to simulate classical deep learning models or problems because of the intractability of deep quantum circuits. Thus, it is necessary to design feasible quantum algorithms for quantum machine learning for noisy intermediate scale quantum (NISQ) devices. This work explores variational quantum circuits for deep reinforcement learning. Specifically, we reshape classical deep reinforcement learning algorithms like experience replay and target network into a representation of variational quantum circuits. Moreover, we use a quantum information encoding scheme to reduce the number of model parameters compared to classical neural networks. To the best of our knowledge, this work is the first proof-of-principle demonstration of variational quantum circuits to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and target network. Besides, our variational quantum circuits can be deployed in many near-term NISQ machines.