Learning governing equations allows for deeper understanding of the structure and dynamics of data. We present a random sampling method for learning structured dynamical systems from under-sampled and possibly noisy state-space measurements. The learning problem takes the form of a sparse least-squares fitting over a large set of candidate functions. Based on a Bernstein-like inequality for partly dependent random variables, we provide theoretical guarantees on the recovery rate of the sparse coefficients and the identification of the candidate functions for the corresponding problem. Computational results are demonstrated on datasets generated by the Lorenz 96 equation, the viscous Burgers' equation, and the two-component reaction-diffusion equations (which is challenging due to parameter sensitives in the model). This formulation has several advantages including ease of use, theoretical guarantees of success, and computational efficiency with respect to ambient dimension and number of candidate functions.
Recursive Sparse Recovery in Large but Structured Noise - Part 2
我们研究递归恢复稀疏向量的时间序列的问题,ST,从测量Mt:= ST + Lt的结构化噪声Lt,这是密集的,可以有很大的幅度损坏。我们需要的结构是,Lt应该位于一个低维子空间中,该子空间要么是固定的,要么变化“足够慢”;并且其协方差矩阵的特征值是“聚类的”。我们不假设稀疏向量序列上的任何模型。它们的支持集和它们的非零元素值可以是独立的,也可以是随时间相关的(通常在许多应用中它们是相关的)。唯一需要的是,有一些支持的变化,每隔一段时间。我们介绍了一种新的解决方案,称为递归投影压缩感知与聚类PCA(ReProCS-cPCA),解决了一些早期工作的局限性。在温和的假设下,我们表明,以高概率,ReProCS-cPCA可以在任何时候都准确地恢复St的支持集;并且St和Lt的重建误差都是由时不变的小值上界的。
Recursive Robust PCA or Recursive Sparse Recovery in Large but Structured Noise
本文研究递归鲁棒主元分析问题。这里,“鲁棒”是指对独立和相关稀疏离群值的鲁棒性。如果离群值是感兴趣的信号,则该问题可以被解释为在存在大的但结构化的噪声Lt的情况下递归地恢复稀疏向量St的时间序列中的一个。我们在Lt上假设的结构是Lt是密集的并且位于固定的或“足够缓慢地”改变的低维子空间中。出现这个问题的一个关键应用是视频监控,其目标是将缓慢变化的背景(Lt)与移动的前景对象(St)分离。为了解决上述问题,我们引入了一种新的解决方案,称为递归投影CS(ReProCS)。在温和的假设下,我们表明,以高概率(w. h. p.),ReProCS能够始终精确地恢复St的支撑集;并且St和Lt的重建误差始终由时不变的小值上界。
Accelerated Structured Alternating Projections for Robust Spectrally Sparse Signal Recovery
University of California, Los Angeles(加州大学洛杉矶分校);Hong Kong University of Science and Technology(香港科技大学);Southwestern University of Finance and Economics(西南财经大学);Shenzhen University(深圳大学)