A Higher Precision Algorithm for Computing the $1$-Wasserstein Distance

Authors: Pankaj K Agarwal, Sharath Raghvendra, Pouyan Shirzadian, Rachita Sowle

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5 EXPERIMENTS In this section, we conduct experiments to show that our algorithms from Section 3 and Section 4 improve the accuracy of the additive approximation algorithms. We test an implementation of our algorithm, written in Python, on discrete probability distributions derived from real-world and synthetic data sets. All tests are executed on a computer with a 2.50 GHz Intel Core i7 processor and 8GB of RAM using a single computation thread. ... As shown in Figure 2 (a) (d), our algorithm runs significantly faster than both the Sinkhorn and the LMR algorithms while producing solutions of similar quality.
Researcher Affiliation Academia Pankaj K. Agarwal1*, Sharath Raghvendra2, Pouyan Shirzadian2, and Rachita Sowle2 1Duke University, 2Virginia Tech
Pseudocode No The paper describes the algorithm steps in prose but does not provide a formal pseudocode block or algorithm box.
Open Source Code No The paper does not provide any statement or link indicating that the source code for their methodology is openly available.
Open Datasets Yes For a real-world dataset, we use the Adult Census Data (UCI repository), which is a point cloud in R6 with continuous features for 35, 000 individuals, divided into two categories by income (Dua & Graff (2017)).
Dataset Splits No The paper mentions datasets but does not provide specific details on how the datasets were split into training, validation, or test sets.
Hardware Specification Yes All tests are executed on a computer with a 2.50 GHz Intel Core i7 processor and 8GB of RAM using a single computation thread.
Software Dependencies No The paper mentions "Python" and refers to "Sinkhorn method (Cuturi (2013))" and "LMR algorithm (Lahn et al. (2019))" as black-boxes, but no specific version numbers for these software components or any other libraries are provided.
Experiment Setup No While the paper states, "We set the parameters of the Sinkhorn and LMR algorithms in such a way that the error produced by them matches with the error produced by our 1-Wasserstein algorithm," this is a high-level goal for setting parameters of other algorithms, not a detailed description of the experimental setup (e.g., learning rates, batch sizes, epochs) for their proposed methods.