Random feature methods have been successful in various machine learning tasks, are easy to compute, and come with theoretical accuracy bounds. They serve as an alternative approach to standard neural networks since they can represent similar function spaces without a costly training phase. However, for accuracy, random feature methods require more measurements than trainable parameters, limiting their use for data-scarce applications or problems in scientific machine learning. This paper introduces the sparse random feature expansion to obtain parsimonious random feature models. Specifically, we leverage ideas from compressive sensing to generate random feature expansions with theoretical guarantees even in the data-scarce setting. In particular, we provide generalization bounds for functions in a certain class (that is dense in a reproducing kernel Hilbert space) depending on the number of samples and the distribution of features. The generalization bounds improve with additional structural conditions, such as coordinate sparsity, compact clusters of the spectrum, or rapid spectral decay. In particular, by introducing sparse features, i.e. features with random sparse weights, we provide improved bounds for low order functions. We show that the sparse random feature expansions outperforms shallow networks in several scientific machine learning tasks.
翻译:随机特性方法在各种机器学习任务中是成功的,很容易计算,并且具有理论精确度。它们可以作为标准神经网络的替代方法,因为它们可以代表类似的功能空间而无需花费培训阶段。然而,为了准确性,随机特性方法需要比可训练参数更多的测量,限制其用于数据偏差应用或科学机器学习中的问题。本文介绍了稀疏随机特性扩展,以获得有腐蚀性的随机特性模型。具体地说,我们利用压缩感应的想法来产生随机特性扩展,同时提供理论保证,甚至数据偏差设置。特别是,我们根据样品的数量和特征分布,为某类(在再生内核Hilbert空间中密集的)的功能提供一般化界限。一般特性界限随着额外的结构条件而改善,例如协调宽度、频谱的紧凑集群或快速光谱衰减。我们通过引入稀疏特性,即随机稀散重量特征,为低顺序功能提供了改进的界限。我们显示,在几个科学网络中,随机特性扩展的随机特性扩展超出了浅质的网络。