Spherical Tree-Sliced Wasserstein Distance

Authors: Viet-Hoang Tran, Thanh Chu, Minh-Khoi Nguyen-Nhat, Trang Pham, Tam Le, Tan Nguyen

ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we conduct a wide range of numerical experiments, including gradient flows and self-supervised learning, to assess the performance of our proposed metric, comparing it to recent benchmarks.
Researcher Affiliation Collaboration Viet-Hoang Tran Department of Mathematics National University of Singapore EMAIL Thanh T. Chu Department of Computer Science National University of Singapore EMAIL Khoi N.M. Nguyen FPT Software AI Center EMAIL Trang Pham Qualcomm AI Research EMAIL Tam Le The Institute of Statistical Mathematics & RIKEN AIP EMAIL Tan M. Nguyen Department of Mathematics National University of Singapore EMAIL
Pseudocode Yes We summarize a pseudo-code for STSW distance computation in Algorithm 1. Algorithm 1 Spherical Tree-Sliced Wasserstein distance.
Open Source Code Yes The code is publicly available at https://github.com/lilythchu/STSW.git.
Open Datasets Yes We train Res Net18 (He et al., 2016) based encoder on the CIFAR-10 (Krizhevsky et al., 2009) w.r.t L. Data used in this task is collected by (Mathieu & Nickel, 2020) which consists of Fire (Brakenridge, 2017), Earthquake (EOSDIS, 2020) and Flood (EOSDIS, 2020).
Dataset Splits Yes Table 7: Earth datasets. Earthquake Flood Fire Train 4284 3412 8966 Test 1836 1463 3843 Data size 6120 4875 12809
Hardware Specification Yes All our experiments were conducted on a single NVIDIA H100 80G GPU.
Software Dependencies No The paper mentions software like ResNet18, Adam optimizer, SGD, but does not provide specific version numbers for these or other libraries/frameworks used.
Experiment Setup Yes The training is conducted over 500 epochs with a full batch size, and each experiment is repeated 10 times. ... We use a mixture of 12 von Mises-Fisher distributions (v MFs) as our target ν. ... We train with Adam (Kinga et al., 2015) optimizer lr = 0.01 over 500 epochs and an additional lr = 0.05 for SSW. ...we train a Res Net18 (He et al., 2016) on CIFAR-10 (Krizhevsky, 2009) data for 200 epochs using a batch size of 512. We use SGD as our optimizer with initial lr = 0.05 a momentum 0.9, and a weight decay 10-3.