arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.03937cs.LGcs.ROcs.SYeess.SYmath.OCstat.ML
收藏

稳定线性动态系统预测与控制的记忆有效学习

Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control

Northwestern University(西北大学);University of Chicago(芝加哥大学)

Giorgos Mamakoukas, Orest Xherija, T. D. Murphey

摘要:

从数据中学习稳定的线性动态系统(LDS)涉及创建模型,这些模型既可以最大限度地减少重建误差,又可以加强学习表示的稳定性。我们提出了一种新的算法学习稳定的LDS。使用最近的稳定矩阵的表征,我们提出了一种优化方法,确保在每一步的稳定性,并迭代地提高重建误差使用本文导出的梯度方向。当应用于LDSs的输入,我们的方法-在目前的方法学习稳定的LDSs-更新的状态和控制矩阵,扩大解决方案的空间,并允许模型具有较低的重建误差。我们将我们的算法在模拟和实验中应用到各种问题,包括从图像序列中学习动态纹理和控制机器人操纵器。与现有的方法相比,我们提出的方法实现了数量级的改善重建误差和优越的控制性能方面的结果。此外,它可以证明是更有效的内存,与O(n^4)的竞争方案相比,它的空间复杂度为O(n^2)空间复杂度,因此当其他方法失败时,可以扩展到更高维的系统。

英文摘要:

Learning a stable Linear Dynamical System (LDS) from data involves creating models that both minimize reconstruction error and enforce stability of the learned representation. We propose a novel algorithm for learning stable LDSs. Using a recent characterization of stable matrices, we present an optimization method that ensures stability at every step and iteratively improves the reconstruction error using gradient directions derived in this paper. When applied to LDSs with inputs, our approach---in contrast to current methods for learning stable LDSs---updates both the state and control matrices, expanding the solution space and allowing for models with lower reconstruction error. We apply our algorithm in simulations and experiments to a variety of problems, including learning dynamic textures from image sequences and controlling a robotic manipulator. Compared to existing approaches, our proposed method achieves an orders-of-magnitude improvement in reconstruction error and superior results in terms of control performance. In addition, it is provably more memory-efficient, with an O(n^2) space complexity compared to O(n^4) of competing alternatives, thus scaling to higher-dimensional systems when the other methods fail.

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。

↑