@inproceedings{37f6af15c2f5430a8e748bd2dae7b0fe,
title = "Nonstationary sparse spectral permanental process",
abstract = "Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model's expressiveness. To overcome these limitations, we propose a novel approach utilizing the sparse spectral representation of nonstationary kernels. This technique relaxes the constraints on kernel types and stationarity, allowing for more flexible modeling while reducing computational complexity to the linear level. Additionally, we introduce a deep kernel variant by hierarchically stacking multiple spectral feature mappings, further enhancing the model's expressiveness to capture complex patterns in data. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of our approach, particularly in scenarios with pronounced data nonstationarity. Additionally, ablation studies are conducted to provide insights into the impact of various hyperparameters on model performance. Code is publicly available at https://github.com/SZC20/DNSSPP.",
author = "Zicheng Sun and Yixuan Zhang and Zenan Ling and Xuhui Fan and Feng Zhou",
year = "2024",
language = "English",
isbn = "9798331314385",
series = "Advances in Neural Information Processing Systems",
publisher = "Curran Associates",
pages = "1--24",
editor = "A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang",
booktitle = "NeurIPS 2024",
note = "Conference on Neural Information Processing Systems (38th : 2024), NeurIPS 2024 ; Conference date: 10-12-2024 Through 15-12-2024",
}