Yueling Zhang — accepted AI-conference papers

2024

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

Hao Di, Haishan Ye, Yueling Zhang, Xiangyu Chang, Guang Dai, Ivor Tsang

ICML 2024spotlight

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise var…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Boosting Verified Training for Robust Image Classifications via Abstraction

Zhaodi Zhang, Zhiyi Xue, Yang Chen, Si Liu, Yueling Zhang, Jing Liu +1

CVPR 2023poster

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on intervals, all the perturbed images that are mapped to the same int…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗