Long Tran-Thanh

Full Professor, The university of Warwick

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

#5315 Spotlight · Hoang Pham, The-Anh Ta, Tom Jacobs, Rebekka Burkholz, Long Tran-Thanh

We study the training dynamic of sparse neural networks through the lens of Graphon where masks of pruning methods converge to graphons as networks' width approach infinite