# Explicit representations for Banach subspaces of Lizorkin distributions

arXiv: https://arxiv.org/abs/2203.05312 · HTML: https://mlsanity.com/paper/2203.05312/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2022.

## Built on by (most cited first, 3 of 3)

- [Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions](https://mlsanity.com/paper/2210.16222/) (2022)
- [From Kernel Methods to Neural Networks: A Unifying Variational Formulation](https://mlsanity.com/paper/2206.14625/) (2022)
- [On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks](https://mlsanity.com/paper/2303.17805/) (2023)

## Abstract (arXiv)

The Lizorkin space is well-suited for studying various operators; e.g., fractional Laplacians and the Radon transform. In this paper, we show that the space is unfortunately not complemented in the Schwartz space. However, we can show that it is dense in C0(mathbb Rd), a property that is shared by the larger Schwartz space and that turns out to be useful for applications. Based on this result, we investigate subspaces of Lizorkin distributions that are Banach spaces and for which a continuous representation operator exists. Then, we introduce a variational framework involving these spaces and that makes use of the constructed operator. By investigating two particular cases of this framework, we are able to strengthen existing results for fractional splines and 2-layer ReLU networks.