News Release

UC San Diego Researchers Earn AISTATS 2025 Test of Time Award

May 5, 2025

We’re thrilled that our lab’s work on “Deeply-Supervised Nets” has received the Test-of-Time Award at AISTATS 2025!  This prestigious award honors papers published 10 years ago that have had a lasting and significant impact on the field of artificial intelligence and statistical modeling.

DSN combats the vanishing and exploding gradient problem when training deep neural networks by having each individual layer directly access the supervised labeling information. This significantly facilitates the training of deep networks.

Congratulations to all authors of this work: Chen-Yu Lee, Saining Xie, Patrick Gallagher, Zhengyou Zhang, and Zhuowen Tu.

Paper: https://arxiv.org/abs/1409.5185
Award slides: https://chl260.github.io/PDF/dsn-aistats-testoftime.pdf
Official announcement: https://x.com/aistats_conf/status/1918958574736150959

The senior author on the paper is UC San Diego cognitive science professor Zhuowen Tu, a faculty member in the Center for Visual Computing at the UC San Diego Jacobs School of Engineering. Tu is a faculty member in the UC San Diego Department of Cognitive Science and an affiliate professor in the Department of Computer Science and Engineering. 

Media Contacts

Daniel Kane
Jacobs School of Engineering
858-534-3262
dbkane@ucsd.edu