Hilbert Curve Projection Distance for Distribution Comparison
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-07 · 46 (7) · 4993-5007
DOI: 10.1109/tpami.2024.3363780 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-07. Verfasst von Tao Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Renmin University of China research fund program for young scholars, Beijing Institute of Technology research fund program for young scholars.
Abstract (Originalsprache)
Distribution comparison plays a central role in many machine learning tasks like data classification and generative modeling. In this study, we propose a novel metric, called Hilbert curve projection (HCP) distance, to measure the distance between two probability distributions with low complexity. In particular, we first project two high-dimensional probability distributions using Hilbert curve to obtain a coupling between them, and then calculate the transport distance between these two distributions in the original space, according to the coupling. We show that HCP distance is a proper metric and is well-defined for probability measures with bounded supports. Furthermore, we demonstrate that the modified empirical HCP distance with the Lp cost in the d-dimensional space converges to its population counterpart at a rate of no more than O(n-1/2max{d,p}). To suppress the curse-of-dimensionality, we also develop two variants of the HCP distance using (learnable) subspace projections. Experiments on both synthetic and real-world data show that our HCP distance works as an effective surrogate of the Wasserstein distance with low complexity and overcomes the drawbacks of the sliced Wasserstein distance.
Förderung
- National Natural Science Foundation of China
- Renmin University of China research fund program for young scholars
- Beijing Institute of Technology research fund program for young scholars
- Beijing Municipal Natural Science Foundation
Zitieren
APA
Li, T., Meng, C., Xu, H., & Yu, J. (2024). Hilbert Curve Projection Distance for Distribution Comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7), 4993-5007. https://doi.org/10.1109/tpami.2024.3363780
Vancouver
Li T, Meng C, Xu H, Yu J. Hilbert Curve Projection Distance for Distribution Comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(7):4993-5007. doi:10.1109/tpami.2024.3363780
BibTeX
@article{Li2024,
author = {Li, Tao and Meng, Cheng and Xu, Hongteng and Yu, Jun},
title = {Hilbert Curve Projection Distance for Distribution Comparison},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {7},
pages = {4993--5007},
doi = {10.1109/tpami.2024.3363780}
}
EUVIMED