The emergence of the Barren Plateau phenomenon poses a significant challenge to quantum machine learning. While most Barren Plateau analyses focus on single-qubit rotation gates, the gradient behavior of Parameterized Quantum Circuits built from multi-qubit gates remains largely unexplored. In this work, we present a general theoretical framework for analyzing the gradient properties of Parameterized Quantum Circuits with multi-qubit gates. Our method generalizes the direct computation framework, bypassing the Haar random assumption on parameters and enabling the calculation of the gradient expectation and variance. We apply this framework to single-layer and deep-layer circuits, deriving analytical results that quantify how gradient variance is co-determined by the size of the multi-qubit gate and the number of qubits, layers, and effective parameters. Numerical simulations validate our findings. Our study provides a refined framework for analyzing and optimizing Parameterized Quantum Circuits with complex multi-qubit gates.
The emergence of the Barren Plateau phenomenon poses a significant challenge to quantum machine learning. While most Barren Plateau analyses focus on single-qubit rotation gates, the gradient behavior of Parameterized Quantum Circuits built from multi-qubit gates remains largely unexplored. In this work, we present a general theoretical framework for analyzing the gradient properties of Parameterized Quantum Circuits with multi-qubit gates. Our method generalizes the direct computation framework, bypassing the Haar random assumption on parameters and enabling the calculation of the gradient expectation and variance. We apply this framework to single-layer and deep-layer circuits, deriving analytical results that quantify how gradient variance is co-determined by the size of the multi-qubit gate and the number of qubits, layers, and effective parameters. Numerical simulations validate our findings. Our study provides a refined framework for analyzing and optimizing Parameterized Quantum Circuits with complex multi-qubit gates.
The barren plateaus phenomenon, where the gradients of parametrized quantum circuits become vanishingly small, poses a significant challenge in quantum machine learning. Foundational analyses of barren plateaus often use methods like the Weingarten formula, which, under the global Haar random assumption, effectively links the gradient variance to the Hilbert space dimension. However, many practical circuits, such as Hardware-Efficient Ans\"atze, utilize a different, non-Haar random model based on the sampling of parameters for single-qubit rotation gates. This study introduces a direct computational method for the gradient expectation and variance, specifically for parametrized quantum circuits constructed from single-qubit rotation gates. Our analysis reveals a direct, quantitative relationship between the gradient variance, circuit depth, and number of effective parameters. Numerical simulations further confirm the validity of our theoretical results. Our findings highlight the role of effective parameters as a key indicator for gradient trainability and provide a precise framework for analyzing barren plateaus in these specific non-Haar random circuits.
Parameterized quantum circuits (PQCs) have emerged as a foundational element in the development and applications of quantum algorithms. However, when initialized with random parameter values, PQCs often exhibit barren plateaus (BP). These plateaus, characterized by vanishing gradients with an increasing number of qubits, hinder optimization in quantum algorithms. In this paper, we analyze the impact of state-of-the-art parameter initialization strategies from classical machine learning in random PQCs from the aspect of BP phenomenon. Our investigation encompasses a spectrum of initialization techniques, including random, Xavier (both normal and uniform variants), He, LeCun, and Orthogonal methods. Empirical assessment reveals a pronounced reduction in variance decay of gradients across all these methodologies compared to the randomly initialized PQCs. Specifically, the Xavier initialization technique outperforms the rest, showing a 62% improvement in variance decay compared to the random initialization. The He, Lecun, and orthogonal methods also display improvements, with respective enhancements of 32 %, 28 %, and 26 %. This compellingly suggests that the adoption of these existing initialization techniques holds the potential to significantly amplify the training efficacy of Quantum Neural Networks (QNNs), a subclass of PQCs. Demonstrating this effect, we employ the identified techniques to train QNNs for learning the identity function, effectively mitigating the adverse effects of BPs. The training performance, ranked from the best to the worst, aligns with the variance decay enhancement as outlined above. This paper underscores the role of tailored parameter initialization in mitigating the BP problem and eventually enhancing the training dynamics of QNNs.
We show the relationship between the Fourier coefficients and the barren plateau problem emerging in parameterized quantum circuits. In particular, the sum of squares of the Fourier coefficients is exponentially restricted concerning the qubits under the barren plateau condition. Throughout theory and numerical experiments, we introduce that this property leads to the vanishing of a probability and an expectation formed by parameterized quantum circuits. The traditional barren plateau problem requires the variance of gradient, whereas our idea does not explicitly need a statistic. Therefore, it is not required to specify the kind of initial probability distribution.
A central challenge in quantum machine learning is understanding the scaling behavior of parameterized quantum circuits (PQCs). In particular, it remains unclear how their performance on unseen data changes as the number of trainable parameters increases. Prior works have derived formal generalization guarantees for quantum models, but it is well-known that many such results do not fully characterize generalization behavior in practice. In this work, we show that gradient-based PQCs can exhibit improved performance on unseen data as model size increases, displaying the phenomenon of double descent. This contrasts with the traditional view that larger models lead to degraded generalization. We provide analytical results rigorously underpinning this behavior by leveraging add-one-in perturbation techniques and spectral properties of random matrices. We support these results with numerical experiments on re-uploading PQCs across several data sets and training set sizes, consistently observing the predicted double descent behavior. While other obstacles on the path toward practical quantum machine learning remain, our finding that deeper parameterized quantum circuits do not necessarily exhibit degraded performance provides reasons for cautious optimism.
Variational quantum algorithms (VQAs) with random structures have poor trainability due to the exponentially vanishing gradient as the circuit depth and the qubit number increase. This result leads to a general belief that a deep circuit will not be feasible. In this work, we provide a viable solution to the vanishing gradient problem for deep VQAs with theoretical guarantees. Specifically, we prove that for quantum controlled-layer and quantum residual network (QResNet), architectures, the expectation of the gradient norm can be lower bounded by a value that is independent of the qubit number and the circuit depth. Our results follow from a careful analysis of the gradient behavior on parameter space consisting of rotation angles, as employed in almost all VQAs, instead of relying on impractical 2-design assumptions. We conduct several numerical experiments as verifications, where only our circuits are trainable and converge, while hardware-efficient and random circuits with similar number of parameters in comparison cannot converge.
Barren plateaus-regions of exponentially small gradients-are a major obstacle for training variational quantum algorithms on non-trivial problem sizes. Existing results analyze specific causes in isolation, such as random deep circuits or global cost functions, but lack a unified picture that integrates circuit design, data encoding, cost structure, and noise. In this work, we develop a comprehensive theory of barren plateaus for parametrized quantum circuits. We prove that three mechanisms jointly control gradient scaling: (1) ansatz-induced concentration, where highly expressive or sufficiently deep circuits approximate unitary 2-designs causing gradient variance to scale as O(2 −n); (2) data-encoding-induced concentration, where certain feature maps wash out class-conditional structure; and (3) probleminduced concentration, where cost functions effectively average over exponentially many degrees of freedom. For each mechanism, we derive explicit scaling laws for the gradient variance as a function of qubit count n, depth L, and encoding complexity. We show that appropriately constrained expressibility, locality, and symmetry breaking can prevent gradients from vanishing exponentially and obtain conditions under which gradients remain at worst polynomially small. This yields architectural and initialization design principles for plateau-resistant circuits, including shallow, problem-informed ansätze, layer-wise training, and structured data encodings. Numerical experiments on up to 100 qubits for VQE, QAOA, and quantum classifiers confirm our theoretical predictions and demonstrate 10-100× improvements in effective gradient magnitudes over standard architectures. Our framework subsumes existing barren plateau results and provides a practical toolkit for diagnosing and mitigating trainability issues in variational quantum algorithms.