Volumetric Optimal Transportation by Fast Fourier Transform
Authors: Na Lei, DONGSHENG An, Min Zhang, Xiaoyin Xu, David Gu
ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that the FFT-OT algorithm is more than a hundred times faster than the conventional methods based on the convex geometry. |
| Researcher Affiliation | Academia | Na Lei Dalian University of Technology nalei@dlut.edu.cn Dongsheng An Stony Brook University doan@cs.stonybrook.edu Min Zhang Zhejiang University min zhang@zju.edu.cn Xiaoyin Xu Harvard Medical School xxu@bwh.harvard.edu Xianfeng Gu Stony Brook University gu@cs.stonybrook.edu |
| Pseudocode | Yes | Algorithm 1: FFT-OT; Algorithm 2: FFT Solver for the Constant Coefficient Elliptic PDE |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | No | The paper describes generating data based on Gaussian mixture models and uses volumetric medical imaging data, but it does not provide concrete access information (link, DOI, citation) for a publicly available dataset. |
| Dataset Splits | No | The paper describes generating samples and grid tessellation but does not specify traditional training, validation, or test dataset splits in terms of percentages or sample counts for an existing dataset. |
| Hardware Specification | Yes | All the experiments are conducted on a Windows laptop with Intel Core i7-7700HQ CPU with 16 GB memory and NVIDIA Ge Force GTX 1060 Graphics Cards. |
| Software Dependencies | No | All the algorithms are developed using generic C++ with CUDA Toolkit. No specific version number is provided for CUDA Toolkit, and C++ is too generic. |
| Experiment Setup | Yes | With the approximation error threshold ε = 1.0 10 6 and the resolution 256 256 256, the running time for our FFT-OT algorithm with double precision on GPU is less than 175 seconds. The domain is tessellated to a 256 256 256 grid. We set σ = σx = σy = σz, and they are 0.83, 0.75 and 0.5 respectively. |