1 code implementation • 11 Jun 2023 • Mengyu Li, Jun Yu, Tao Li, Cheng Meng
Sinkhorn algorithm has been used pervasively to approximate the solution to optimal transport (OT) and unbalanced optimal transport (UOT) problems.
no code implementations • 31 May 2022 • Jingyi Zhang, Cheng Meng, Jun Yu, Mengrui Zhang, Wenxuan Zhong, Ping Ma
Theoretically, we show the selected subsample can be used for efficient density estimation by deriving the convergence rate for the proposed subsample kernel density estimator.
1 code implementation • 30 May 2022 • Tao Li, Cheng Meng, Hongteng Xu, Jun Yu
Distribution comparison plays a central role in many machine learning tasks like data classification and generative modeling.
1 code implementation • 26 May 2022 • Mengyu Li, Jun Yu, Hongteng Xu, Cheng Meng
As a valid metric of metric-measure spaces, Gromov-Wasserstein (GW) distance has shown the potential for matching problems of structured data like point clouds and graphs.
1 code implementation • NeurIPS 2019 • Cheng Meng, Yuan Ke, Jingyi Zhang, Mengrui Zhang, Wenxuan Zhong, Ping Ma
We theoretically show the proposed dimension reduction method can consistently estimate the most ``informative'' projection direction in each iteration.
1 code implementation • NeurIPS 2020 • Cheng Meng, Jun Yu, Jingyi Zhang, Ping Ma, Wenxuan Zhong
The proposed method, named principal optimal transport direction (POTD), estimates the basis of the SDR subspace using the principal directions of the optimal transport coupling between the data respecting different response categories.