Hoang-Chau Luong

lhchau20 (at) apcs (dot) fitus (dot) edu (dot) vn

I am currently a Ph.D. student in the Golisano College of Computing and Information Sciences (GCCIS) at Rochester Institute of Technology (RIT), where I am fortunate to be advised by Professor Lingwei Chen. Before that, I obtained my Bachelor’s degree in CS from the Advanced Program in Computer Science at Ho Chi Minh City University of Science, Vietnam, one of the top undergraduate programs in Vietnam, where I was fortunate to be advised by Professor Minh-Triet Tran.

I am a hard-working and passionate researcher focusing on fundamental problems in deep learning. My research aims to understand why certain methods succeed and how to improve them to achieve better generalization and robustness.

news

Oct 02, 2024	Our paper, Improving Resistance to Noisy Label Fitting by Reweighting Gradients in SAM, is submitted.
Sep 26, 2024	Our paper, Fundamental Convergence Analysis of Sharpness-Aware Minimization, has been accepted in Advances in Neural Information Processing Systems (NeurIPS) 2024.

selected publications

Conference
Fundamental Convergence Analysis of Sharpness-Aware Minimization

Pham Duy Khanh, Hoang-Chau Luong, Boris S Mordukhovich, and 1 more author

Advances in Neural Information Processing Systems, 2024

Abs Bib HTML

The paper investigates the fundamental convergence properties of Sharpness-Aware Minimization (SAM), a recently proposed gradient-based optimization method (Foret et al., 2021) that significantly improves the generalization of deep neural networks. The convergence properties including the stationarity of accumulation points, the convergence of the sequence of gradients to the origin, the sequence of function values to the optimal value, and the sequence of iterates to the optimal solution are established for the method. The universality of the provided convergence analysis based on inexact gradient descent frameworks (Khanh et al., 2023b) allows its extensions to the normalized versions of SAM such as VaSSO (Li & Giannakis, 2023), RSAM (Liu et al., 2022), and to the unnormalized versions of SAM such as USAM (Andriushchenko & Flammarion, 2022). Numerical experiments are conducted on classification tasks using deep learning models to confirm the practical aspects of our analysis.
@article{klmtneurips, title = {Fundamental Convergence Analysis of Sharpness-Aware Minimization}, author = {Khanh, Pham Duy and Luong, Hoang-Chau and Mordukhovich, Boris S and Tran, Dat Ba}, journal = {Advances in Neural Information Processing Systems}, year = {2024}, url = {https://arxiv.org/abs/2401.08060}, dimensions = {true}, }