Explicit Regularization in Overparametrized Models via Noise Injection


METADATA ONLY
Loading...

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Injecting noise within gradient descent has several desirable features, such as smoothing and regularizing properties. In this paper, we investigate the effects of injecting noise before computing a gradient step. We demonstrate that small perturbations can induce explicit regularization for simple models based on the L1-norm, group L1-norms, or nuclear norms. However, when applied to overparametrized neural networks with large widths, we show that the same perturbations can cause variance explosion. To overcome this, we propose using independent layer-wise perturbations, which provably allow for explicit regularization without variance explosion. Our empirical results show that these small perturbations lead to improved generalization performance compared to vanilla gradient descent.

Publication status

published

Book title

Proceedings of The 26th International Conference on Artificial Intelligence and Statistics

Volume

206

Pages / Article No.

7265 - 7287

Publisher

PMLR

Event

26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09462 - Hofmann, Thomas / Hofmann, Thomas check_circle

Notes

Funding

Related publications and datasets