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 2207.06128math.NAcs.NA
收藏

组合稀疏性、逼近类与参数输运方程

Compositional Sparsity, Approximation Classes, and Parametric Transport Equations

Wolfgang Dahmen

AI总结:

该研究提出基于组合维数稀疏性的高维函数模型通用框架,阐释深度神经网络规避维数灾难的机制,并通过参数输运方程解流形验证其有效性,得到可规避维数灾难的神经网络收敛速率。

摘要:

逼近多变量函数面临的特殊挑战通常被归为“维数灾难(Curse of Dimensionality, CoD)”范畴。除非被逼近函数具有极高的光滑度,否则只能通过利用某种通常隐含的结构稀疏性来规避维数灾难。本文提出了一个适用于高维函数新模型类的通用框架,这类模型基于合适的“组合维数稀疏性”概念,在连续层面上量化具有特定结构性质的复合函数的逼近能力,尤其阐释了深度神经网络可规避维数灾难的适用场景。\n本文通过参数输运方程的解流形验证了这些概念的实用性。对于这类偏微分方程(PDE),参数到解的映射不具备高阶正则性,而这类正则性正是其他模型场景下传统方法规避维数灾难的关键。研究证明,组合稀疏性是证明问题数据的稀疏性能够以可量化的方式被解流形继承的核心机制,尤其能得到深度神经网络实现的收敛速率,证实维数灾难确实可被规避。

英文摘要:

Approximating functions of a large number of variables poses particular challenges often subsumed under the term ``Curse of Dimensionality'' (CoD). Unless the approximated function exhibits a very high level of smoothness the CoD can be avoided only by exploiting some typically hidden {\em structural sparsity}. In this paper we propose a general framework for new model classes of functions in high dimensions. They are based on suitable notions of {\em compositional dimension-sparsity} quantifying, on a continuous level, approximability by compositions with certain structural properties. In particular, this describes scenarios where deep neural networks can avoid the CoD. The relevance of these concepts is demonstrated for {\em solution manifolds} of parametric transport equations. For such PDEs parameter-to-solution maps do not enjoy the type of high order regularity that helps to avoid the CoD by more conventional methods in other model scenarios. Compositional sparsity is shown to serve as the key mechanism forn proving that sparsity of problem data is inherited in a quantifiable way by the solution manifold. In particular, one obtains convergence rates for deep neural network realizations showing that the CoD is indeed avoided.

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。

↑