AI 中文总结
研究在INT8 NPU上零阶设备端训练中梯度样本数量q的影响及优化难题，提出自适应算法QScheduler，可依训练进度调整q，实验表明该算法在EuroSAT和STL-10数据集上，与固定q配置效果相当且无需事先优化超参数。
AI 中文摘要
零阶（ZO）优化通过仅前向传递估计梯度，实现了在配备 NPU 的微控制器上进行设备端学习（ODL），无需反向传播原语并降低内存需求。梯度样本数量q对训练有关键影响：样本不足会产生噪声梯度导致早期停滞，样本过多则消耗更多计算资源。然而，找到最优q通常需要昂贵的超参数搜索。本文介绍了QScheduler，一种基于训练进度调整q的自适应算法，并首次在STM32N6的Neural-ART NPU上提供了INT8量化设备端训练的概念验证。在EuroSAT和STL-10上的实验表明，QScheduler在ResNet18和MobileNetV2上与调优良好的固定q配置匹配良好，无需事先进行q超参数优化。
英文摘要
Zeroth-Order (ZO) optimization enables On-Device Learning (ODL) on NPU-equipped microcontrollers by estimating gradients through forward passes alone, bypassing the need for backpropagation primitives and reducing memory requirements. The number of gradient samples q critically affects training: insufficient samples produce noisy gradients that plateau early, while excessive samples consume more computational resources. However, finding an optimal q typically requires costly hyperparameter searches. This work introduces QScheduler, an adaptive algorithm that adjusts q based on training progress, and provides the first proof-of-concept of INT8 quantized on-device training on the STM32N6's Neural-ART NPU. Experiments on EuroSAT and STL-10 show that QScheduler matches well-tuned fixed-q configurations for both ResNet18 and MobileNetV2, without requiring prior q hyperparameter optimization.
Journal refInternational Joint Conference on Neural Networks, Jun 2026, Maastricht, Netherlands
