Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions

Authors: Khai Nguyen, Nhat Ho

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we demonstrate the favorable performance of H2SW in 3D mesh deformation, deep 3D mesh autoencoders, and datasets comparison1.
Researcher Affiliation Academia Khai Nguyen Department of Statistics and Data Sciences The University of Texas at Austin Austin, TX 78712 khainb@utexas.edu Nhat Ho Department of Statistics and Data Sciences The University of Texas at Austin Austin, TX 78712 minhnhat@utexas.edu
Pseudocode No The paper describes the algorithms and transformations conceptually and mathematically, but it does not include any explicitly labeled "Pseudocode" or "Algorithm" blocks with structured steps.
Open Source Code Yes Code for this paper is published at https://github.com/khainb/H2SW.
Open Datasets Yes We utilize the processed Shape Net dataset [12] from [46]... We uses MNIST [31] dataset, EMNIST dataset [14], Fashion MNIST dataset [56], KMNIST dataset [13], and USPS dataset [24].
Dataset Splits No The paper mentions "training set" and "testing set" but does not explicitly describe a "validation set" or provide specific percentages/counts for a validation split.
Hardware Specification Yes For 3D mesh autoencoder experiments, we use a single NVIDIA A100 GPU.
Software Dependencies No The paper mentions using specific software/libraries like Point-Net and an SGD optimizer, but it does not specify version numbers for any of these components.
Experiment Setup Yes We utilize the Euler discretization scheme with step size 0.01 and 5000 steps. ...We train the autoencoder for 2000 epochs on the training set of the Shape Net dataset using an SGD optimizer with a learning rate of 1e 3, and a batch size of 128.