Random-Matrix-Induced Simplicity Bias in Over-parameterized Variational Quantum Circuits
This addresses a critical problem in quantum machine learning by providing a theoretical framework to understand and mitigate trainability issues in variational quantum algorithms, offering insights for designing more effective architectures.
The paper explains that over-parameterized variational quantum circuits (VQCs) often suffer from poor trainability and generalization due to a 'simplicity bias' where the hypothesis class collapses to near-constant functions, with barren plateaus as a consequence, and shows that tensor-structured VQCs avoid this collapse by preserving output variability and gradient signals.
Over-parameterization is commonly used to increase the expressivity of variational quantum circuits (VQCs), yet deeper and more highly parameterized circuits often exhibit poor trainability and limited generalization. In this work, we provide a theoretical explanation for this phenomenon from a function-class perspective. We show that sufficiently expressive, unstructured variational ansatze enter a Haar-like universality class in which both observable expectation values and parameter gradients concentrate exponentially with system size. As a consequence, the hypothesis class induced by such circuits collapses with high probability to a narrow family of near-constant functions, a phenomenon we term simplicity bias, with barren plateaus arising as a consequence rather than the root cause. Using tools from random matrix theory and concentration of measure, we rigorously characterize this universality class and establish uniform hypothesis-class collapse over finite datasets. We further show that this collapse is not unavoidable: tensor-structured VQCs, including tensor-network-based and tensor-hypernetwork parameterizations, lie outside the Haar-like universality class. By restricting the accessible unitary ensemble through bounded tensor rank or bond dimension, these architectures prevent concentration of measure, preserve output variability for local observables, and retain non-degenerate gradient signals even in over-parameterized regimes. Together, our results unify barren plateaus, expressivity limits, and generalization collapse under a single structural mechanism rooted in random-matrix universality, highlighting the central role of architectural inductive bias in variational quantum algorithms.