today local_bar

Shihao Hou

MS student, Xiamen University

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster

#3410 · Shriram M S, Xinyue Hao, Shihao Hou, Yang Lu, Laura Sevilla-Lara, Anurag Arnab, Shreyank N Gowda

We make neural network training cheaper and more accurate by progressively dropping parts of the data after each epoch.