View a PDF of the paper titled Representation Learning with Quantum Signal Processing, by Junqi Wang and Junyu Liu
Abstract:Representation learning begins when training changes the features that define similarity between data. A frozen-kernel model only reweights a fixed geometry. We establish quantum signal processing (QSP) as a solvable quantum model of the representation-learning regime. At arbitrary depth, we compute the exact mean and variance of its quantum neural tangent kernel, revealing an input-dependent angular geometry whose diagonal remains non-self-averaging even when the underlying unitary approaches Haar randomness. We also prove a sparse-data guarantee for the full nonlinear gradient flow without freezing or ensemble-averaging the kernel: the realized dynamics converges to an integrable scalar flow with a time-dependent kernel closure and explicit convergence times. A finite-depth speed limit holds for every data set and trajectory. At higher data density, numerical results show coupled evolution beyond both the scalar and frozen-kernel descriptions. These results give a controlled theory of learned quantum data geometry with provable training dynamics beyond the frozen limit.
Submission history
From: Junqi Wang [view email]
[v1]
Fri, 28 Aug 2026 19:57:26 UTC (89 KB)
[v2]
Mon, 16 Nov 2026 23:58:59 UTC (98 KB)
![[2608.28828] Representation Learning with Quantum Signal Processing [2608.28828] Representation Learning with Quantum Signal Processing](https://techwavedispatch.com/wp-content/uploads/2026/11/260828828-Representation-Learning-with-Quantum-Signal-Processing-1024x597.png)