6 papers
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data
Zhi-Yong Wang, Hao Nan Sheng, Werner Stefan +3
Federated learning distributes data among clients, making it vulnerable to malicious attacks and data heterogeneity, which together pose challenges for robust learning. To tack…
AROMA: Autonomous Rank-one Matrix Adaptation
Hao Nan Sheng, Zhi-yong Wang, Mingrui Yang +1
As large language models continue to grow in size, parameter-efficient fine-tuning (PEFT) has become increasingly crucial. While low-rank adaptation (LoRA) offers a solution throug…
Low-Rank Tensor Completion via Novel Sparsity-Inducing Regularizers
Zhi-Yong Wang, Hing Cheung So, Abdelhak M. Zoubir
To alleviate the bias generated by the l1-norm in the low-rank tensor completion problem, nonconvex surrogates/regularizers have been suggested to replace the tensor nuclear norm,…
A framework to generate sparsity-inducing regularizers for enhanced low-rank matrix completion
Zhi-Yong Wang, Hing Cheung So
Applying half-quadratic optimization to loss functions can yield the corresponding regularizers, while these regularizers are usually not sparsity-inducing regularizers (SIRs). To…
Robust matrix completion via Novel M-estimator Functions
Zhi-Yong Wang, Hing Cheung So
M-estmators including the Welsch and Cauchy have been widely adopted for robustness against outliers, but they also down-weigh the uncontaminated data. To address this issue, we de…
Robust Low-Rank Matrix Completion via a New Sparsity-Inducing Regularizer
Zhi-Yong Wang, Hing Cheung So, Abdelhak M. Zoubir
This paper presents a novel loss function referred to as hybrid ordinary-Welsch (HOW) and a new sparsity-inducing regularizer associated with HOW. We theoretically show that the re…