Preprint
Universal Approximation Under Constraints is Possible with Transformers
Abstract
Many practical problems need the output of a machine learning model to
satisfy a set of constraints, $K$. Nevertheless, there is no known guarantee
Authors
Kratsios A; Zamanlooy B; Liu T; Dokmanić I
Publication date
October 7, 2021
DOI
10.48550/arxiv.2110.03303
Preprint server
arXiv