4 papers
Hyperball May Not Be a Free Lunch
Yihao Xiao, Jialong Sun, Zitian Gao +5
For scale-invariant deep networks, Hyperball-style optimizers have shown strong performance in large-scale training by fixing the norms of matrix-valued parameters and normalizing…
SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
Jialong Sun, Zeming Wei, Jiaxuan Zou +6
Machine unlearning (MU) is essential for enforcing the right to be forgotten in machine learning systems. A key challenge of MU is how to reliably audit whether a model has truly f…
Taming Generative Synthetic Data for X-ray Prohibited Item Detection
Jialong Sun, Hongguang Zhu, Weizhe Liu +3
Training prohibited item detection models requires a large amount of X-ray security images, but collecting and annotating these images is time-consuming and laborious. To address d…
FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks
Jialong Sun, Xinpeng Ling, Jiaxuan Zou +2
The inherent autocorrelation of time series data presents an ongoing challenge to multivariate time series prediction. Recently, a widely adopted approach has been the incorporatio…