Mitigating Barren Plateaus in Quantum Neural Networks via an AI-Driven Submartingale-Based Framework

Jun Zhuang, Chaowen Guan

Keywords: Quantum Machine Learning, Barren Plateaus, Martingale, Generative Models, Large Language Models

TL;DR: We propose AdaInit, a novel AI-driven submartingale-based framework that adaptively generates effective initial parameters for quantum neural networks to mitigate barren plateaus by leveraging generative models with the submartingale property.

Abstract: In the era of noisy intermediate-scale quantum (NISQ) computing, Quantum Neural Networks (QNNs) have emerged as a promising approach for various applications, yet their training is often hindered by barren plateaus (BPs), where gradient variance vanishes exponentially in terms of the qubit size. Most existing initialization-based mitigation strategies rely heavily on pre-designed static parameter distributions, thereby lacking adaptability to diverse model sizes or data conditions. To address these limitations, we propose AdaInit, a foundational framework that leverages generative models with the submartingale property to iteratively synthesize initial parameters for QNNs that yield non-negligible gradient variance, thereby mitigating BPs. Unlike conventional one-shot initialization methods, AdaInit adaptively explores the parameter space by incorporating dataset characteristics and gradient feedback, with theoretical guarantees of convergence to finding a set of effective initial parameters for QNNs. We provide rigorous theoretical analyses of the submartingale-based process and empirically validate that AdaInit consistently outperforms existing initialization methods in maintaining higher gradient variance across various QNN scales. We believe this work may initiate a new avenue to mitigate BPs.

Primary Area: optimization

Submission Number: 7184