most citedDP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2023

MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies

Shiyue Zhang, Shijie Wu, Ozan Irsoy +4

Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P -- that is, minimizing the forward cross-…