Elementary superexpressive activations

Authors: Dmitry Yarotsky

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical First, our existence result (Theorem 3) is of course purely theoretical: though the network is small, a huge approximation complexity is hidden in the very special choice of the network weights.
Researcher Affiliation Academia 1Skolkovo Institute of Science and Technology, Moscow, Russia. Correspondence to: Dmitry Yarotsky <d.yarotsky@skoltech.ru>.
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No This paper is theoretical and does not describe a methodology with associated source code for release.
Open Datasets No This is a theoretical paper and does not describe experiments using a dataset, hence no information about dataset availability for training.
Dataset Splits No This is a theoretical paper and does not describe experiments requiring training/validation/test splits.
Hardware Specification No This is a theoretical paper and does not describe experiments, thus no hardware specifications are mentioned.
Software Dependencies No This is a theoretical paper and does not describe experiments, thus no software dependencies are mentioned.
Experiment Setup No This is a theoretical paper and does not describe any experimental setup or hyperparameters.