LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

TL;DR

LieTrunc-QNN introduces a geometric framework using Lie algebra truncation to enhance trainability and expressivity in quantum neural networks, addressing issues like barren plateaus and noise fragility.

Contribution

The paper develops a novel algebraic-geometric approach to analyze and improve quantum neural network trainability and expressivity through Lie algebra structures.

Findings

LieTrunc-QNN maintains stable gradients and high effective dimension in experiments.

Increasing effective dimension causes exponential gradient suppression without structured truncation.

Polynomial decay of gradient variance is achieved in the proposed framework.

Abstract

Quantum Machine Learning (QML) is fundamentally limited by two challenges: barren plateaus (exponentially vanishing gradients) and the fragility of parameterized quantum circuits under noise. Despite extensive empirical studies, a unified theoretical framework remains lacking. We introduce LieTrunc-QNN, an algebraic-geometric framework that characterizes trainability via Lie-generated dynamics. Parameterized quantum circuits are modeled as Lie subalgebras of u(2^n), whose action induces a Riemannian manifold of reachable quantum states. Expressivity is reinterpreted as intrinsic manifold dimension and geometry. We establish a geometric capacity-plateau principle: increasing effective dimension leads to exponential gradient suppression due to concentration of measure. By restricting to structured Lie subalgebras (LieTrunc), the manifold is contracted, preventing concentration and preserving non-degenerate gradients. We prove two main results: (1) a trainability lower bound for LieTrunc-QNN, and (2) that the Fubini-Study metric rank is bounded by the algebraic span of generators, showing expressivity is governed by structure rather than parameter count. Compact Lie subalgebras also provide inherent robustness to perturbations. Importantly, we establish a polynomial trainability regime where gradient variance decays polynomially instead of exponentially. Experiments (n=2-6) validate the theory: LieTrunc-QNN maintains stable gradients and high effective dimension, while random truncation leads to metric rank collapse. At n=6, full metric rank is preserved (rank=16). Results support a scaling law between gradient variance and effective dimension. This work provides a unified geometric framework for QNN design, linking Lie algebra, manifold geometry, and optimization.