.png){kind=icon}
.png){kind=icon}
Return
Per-example gradient regularization improves learning signals from noisy data
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-024-06661-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Gradient regularization, as described in Barrett and Dherin (in: International conference on learning representations, 2021), is a highly effective technique for promoting flat minima during gradient descent. Empirical evidence suggests that this regularization technique can significantly enhance the robustness of deep learning models against noisy perturbations, while also reducing test error. In this paper, we explore the per-example gradient regularization (PEGR) and present a theoretical analysis that demonstrates its effectiveness in improving both test error and robustness against noise perturbations. Specifically, we adopt a signal-noise data model from Cao et al. (Adv Neural Inf Process Syst 35:25237-25250, 2022) and show that PEGR can learn signals effectively while suppressing noise memorization. In contrast, standard gradient descent struggles to distinguish the signal from the noise, leading to suboptimal generalization performance. Our analysis reveals that PEGR penalizes the variance of pattern learning, thus effectively suppressing the memorization of noises from the training data. These findings underscore the importance of variance control in deep learning training and offer useful insights for developing more effective training approaches.
Keywords:
Gradient regularization
Noise perturbations
Variance control