arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.08155stat.MLcs.LGmath.DSmath.OC
收藏

基于动力系统的降维框架

A dynamical systems based framework for dimension reduction

University of Utah(犹他大学)

Ryeongkyung Yoon, Braxton Osting

摘要:

我们提出了一个新的框架,学习低维表示的数据的非线性动力系统的基础上,我们称之为动态降维(DDR)。在DDR模型中,每个点通过非线性流向低维子空间演化;在子空间上的投影给出了低维嵌入。训练模型包括识别非线性流和子空间。遵循方程发现方法,我们使用字典元素的线性组合来表示定义流的向量场,其中每个元素是预先指定的线性/非线性候选函数。平均总动能的正则化项也被引入和最优输运理论的动机。我们证明了由此产生的优化问题是适定的,并建立了DDR方法的几个属性。我们还展示了如何使用基于梯度的优化方法来训练DDR方法,其中梯度是使用最优控制理论的伴随方法来计算的。DDR方法的合成和示例数据集上实现和比较其他降维方法,包括PCA,t-SNE,和Umap。

英文摘要:

We propose a novel framework for learning a low-dimensional representation of data based on nonlinear dynamical systems, which we call dynamical dimension reduction (DDR). In the DDR model, each point is evolved via a nonlinear flow towards a lower-dimensional subspace; the projection onto the subspace gives the low-dimensional embedding. Training the model involves identifying the nonlinear flow and the subspace. Following the equation discovery method, we represent the vector field that defines the flow using a linear combination of dictionary elements, where each element is a pre-specified linear/nonlinear candidate function. A regularization term for the average total kinetic energy is also introduced and motivated by optimal transport theory. We prove that the resulting optimization problem is well-posed and establish several properties of the DDR method. We also show how the DDR method can be trained using a gradient-based optimization method, where the gradients are computed using the adjoint method from optimal control theory. The DDR method is implemented and compared on synthetic and example datasets to other dimension reductions methods, including PCA, t-SNE, and Umap.

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。

↑