外观
论文arXiv 2610.2208413 天前
学习改变世界，而所学也随之改变：在控制回路中训练与部署神经网络
原文链接：Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop（arXiv 2610.22084 · 发布日期：2026-10-15）
Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop
针对闭环控制中离线训练神经网络引发的分布偏移，提出失效分类与在线适应策略，并在非线性Duffing振子上验证。
核心要点
- 动机是离线训练的神经网络部署到闭环后会改变其训练所依赖的状态分布。
- 提出统一分类，涵盖闭环识别误差、部署诱发的动作误差和持续跟踪误差。
- 通过离散时间灵敏度分析形式化说明离线学习参数会导致部署后的局部轨迹发散。
- 提出基于时间尺度分离在线适应的设计策略，消融显示有界连续学习可缓解轨迹发散。
验证范围与局限：验证范围为非线性Duffing振子上的消融研究。
英文摘要 (Abstract)
Neural networks offer critical adaptability for controlling complex systems where nominal modeling proves intractable. However, when offline-trained neural networks are deployed within closed-loop control systems, their actions fundamentally alter the state distribution upon which they were trained. This paper introduces a unified taxonomy to categorize these sequential failure modes: the initial Closed-Loop Identification Error, the deployment-induced Action Error, and the continuous Tracking Error. Through discrete-time sensitivity analysis, this work formalizes how offline-learned parameters locally guarantee a trajectory divergence upon deployment, degrading performance due to local loss geometry. To mitigate this distribution shift, we propose actionable design policies centered on time-scale separated online adaptation. These mechanisms are validated through ablation studies on a nonlinear Duffing oscillator, demonstrating that bounded continuous learning successfully mitigates trajectory divergence whereas static deployments fail, offering concrete guidelines for practitioners deploying machine learning components in safety-critical feedback systems.
作者：Vittorio Lippi
来源
本页事实对应的公开页面，以原文为准。