Asymptotics of smoothed Wasserstein distances in the small noise regime

Authors: Yunzi Ding, Jonathan Niles-Weed

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental For each of these GOT tasks, we draw 200 samples from the source distribution µk Nσ and target distribution ν Nσ, and use the empirical W2 distance as an estimate of the true W2(µk Nσ, ν Nσ). We repeat the process 100 times and report the mean, as shown in the following figures.
Researcher Affiliation Academia 1Courant Institute of Mathematical Sciences, NYU 2Courant Institute of Mathematical Sciences and the Center for Data Science, NYU
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [No]
Open Datasets No The paper describes drawing samples for numerical examples but does not mention using or providing access information for a publicly available or open dataset.
Dataset Splits No The paper describes drawing samples for numerical examples but does not specify explicit training/validation/test dataset splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library names with version numbers, used to replicate the experiments.
Experiment Setup No The numerical example describes the number of samples drawn and repetitions, but it does not provide specific hyperparameters or system-level training settings as would be found in a machine learning experiment.