Protecting Split Learning by Potential Energy Loss
Abstract
The principal portfolio approach is an emerging method in signal-based trading. However, these principal portfolios may not be diversified to explore the key features of the prediction matrix or robust to different situations. To address this problem, we propose a novel linear trading position with sparse spectrum that can explore a larger spectral region of the prediction matrix. We also develop a Krasnosel'skii-Mann fixed-point algorithm to optimize this trading position, which possesses the descent property and achieves a linear convergence rate in the objective value. This is a new theoretical result for this type of algorithms. Extensive experiments show that the proposed method achieves good and robust performance in various situations.
Cite
Text
Zheng et al. "Protecting Split Learning by Potential Energy Loss." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/618Markdown
[Zheng et al. "Protecting Split Learning by Potential Energy Loss." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/zheng2024ijcai-protecting/) doi:10.24963/ijcai.2024/618BibTeX
@inproceedings{zheng2024ijcai-protecting,
title = {{Protecting Split Learning by Potential Energy Loss}},
author = {Zheng, Fei and Chen, Chaochao and Lyu, Lingjuan and Fu, Xinyi and Fu, Xing and Wang, Weiqiang and Zheng, Xiaolin and Yin, Jianwei},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {5590-5598},
doi = {10.24963/ijcai.2024/618},
url = {https://mlanthology.org/ijcai/2024/zheng2024ijcai-protecting/}
}