arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.09707cs.LGcs.AI
收藏

面向通用约束的高效神经网络学习自适应数据采集

Adaptive Data Harvesting for Efficient Neural Network Learning with Universal Constraints

University of Illinois Chicago(伊利诺伊大学芝加哥分校)

Siteng Kang, Xinhua Zhang

AI总结:

本文提出通过强化学习动态调整样本以提升神经网络在连续域中满足通用约束的效率与稳定性,验证了其在Lyapunov NN和PINNs中的有效性及广泛适用性。

摘要:

训练神经网络以在连续域中满足通用约束具有独特挑战。常见的例子包括Lyapunov神经网络(Lyapunov NNs)和物理信息神经网络(PINNs),其中解析解通常不可用或过于严格。因此,基于采样的方法常用于强制这些约束,而样本的选择对收敛速度、稳定性和解质量有重大影响。现有方法大多依赖固定启发式或手工规则,实际效果不佳。本文旨在通过从数据和经验中学习,动态且迭代地调整样本以响应模型的演变学习性能。通过强化学习训练的策略在测试问题中提高了经验约束满足度,同时显著提升了效率。我们在Lyapunov NN和PINNs上验证了该方法,并展示了其在需要自适应输入选择以有效训练的领域中的广泛应用性。

英文摘要:

Training neural networks to satisfy universal constraints over continuous domains poses unique challenges. Common examples include Lyapunov Neural Networks (Lyapunov NNs) and Physics-Informed Neural Networks (PINNs), where analytical solutions are generally either unavailable or overly restrictive. Sample-based methods are therefore commonly used to enforce these constraints, and the choice of samples has a substantial impact on convergence speed, stability, and solution quality. Most existing methods rely on fixed heuristics or handcrafted rules, and are suboptimal in practice. In this paper, we aim to improve upon them by learning, from data and experience, how to dynamically and iteratively adjust the samples in response to the model's evolving learning performance. Trained by reinforcement learning, the learned policy improves empirical constraint satisfaction on test problems while significantly improving efficiency. We validate the approach on both Lyapunov NNs and PINNs, and demonstrate its broader applicability to domains where adaptive input selection is essential for effective training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑