most citedInitialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

3 citations · 12 across the 10 of their papers we have counts for

collaborators

10 papers

cs.LG2024

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy

Tao Li, Weisen Jiang, Fanghui Liu +2

Pre-training followed by fine-tuning is widely adopted among practitioners. The performance can be improved by "model soups"~\cite{wortsman2022model} via exploring various hyperpar…

stat.ML2024

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Yihang Chen, Fanghui Liu, Taiji Suzuki +1

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of h…

cs.LG20241 cited

Robust NAS under adversarial training: benchmark, theory, and beyond

Yongtao Wu, Fanghui Liu, Carl-Johann Simon-Gabriel +2

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence o…

cs.LG2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Yihang Chen, Fanghui Liu, Yiping Lu +2

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \…

cs.LG20242 cited

Efficient local linearity regularization to overcome catastrophic overfitting

Elias Abad Rocamora, Fanghui Liu, Grigorios G. Chrysos +2

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-ste…

cs.LG20231 cited

On the Convergence of Encoder-only Shallow Transformers

Yongtao Wu, Fanghui Liu, Grigorios G Chrysos +1

In this paper, we aim to build the global convergence theory of encoder-only shallow Transformers under a realistic setting from the perspective of architectures, initialization, a…