Search papers, labs, and topics across Lattice.
This study empirically characterizes the learning dynamics of a compact hybrid quantum forecasting model by comparing it to a classical baseline, focusing on Neural Tangent Kernel (NTK) dynamics. The findings reveal that while the classical model shows stronger early target alignment, the hybrid model achieves similar performance with fewer parameters and faster convergence in most frequency conditions. Importantly, the research uncovers that different optimization geometries can lead to comparable generalization, challenging the assumption that endpoint accuracy alone reflects learning efficacy.
Hybrid quantum models can achieve competitive forecasting performance with fewer parameters and distinct learning trajectories compared to classical counterparts.
We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. Using stationary harmonic-mixture and nonstationary chirp benchmarks with controlled spectral complexity and data availability, we analyze empirical Neural Tangent Kernel dynamics through kernel-target alignment, kernel drift, spectral concentration, and training loss. The classical model exhibits stronger early target alignment, whereas the hybrid model generally develops a less concentrated kernel spectrum and smaller kernel drift. Despite these distinct optimization geometries, both architectures attain similar held-out performance across the evaluated regimes. Notably, the hybrid model uses 125 trainable parameters compared with 281 for the classical baseline and reaches its validation-selected checkpoint earlier in 15 of 18 frequency conditions. A Fourier-augmented classical baseline does not reproduce the observed training behavior, while a controlled re-uploading ablation shows that repeated encoding systematically modifies both optimization and kernel geometry. These results demonstrate that comparable generalization can emerge from substantially different learning trajectories and that individual NTK diagnostics do not provide monotonic predictors of validation convergence. Rather than claiming a general quantum advantage, the study identifies architecture-dependent learning behavior that is masked by endpoint accuracy alone.
