How reparametrization trick broke differentially-private text representation learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Habernal, Ivan
Format:	Preprint
Published:	2022
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2202.12138