Topologically Densified Distributions
From MaRDI portal
Publication:6334639
arXiv2002.04805MaRDI QIDQ6334639
Author name not available (Why is that?)
Publication date: 12 February 2020
Abstract: We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift focus from architectural properties, such as norms on the network weights, to properties of the internal representations before a linear classifier. Specifically, we impose a topological constraint on samples drawn from the probability measure induced in that space. This provably leads to mass concentration effects around the representations of training instances, i.e., a property beneficial for generalization. By leveraging previous work to impose topological constraints in a neural network setting, we provide empirical evidence (across various vision benchmarks) to support our claim for better generalization.
Has companion code repository: https://github.com/c-hofer/topologically_densified_distributions
This page was built for publication: Topologically Densified Distributions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6334639)
