On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

Authors: Andi Han, Bamdev Mishra, Pratik Kumar Jawanpuria, Junbin Gao

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various applications support our findings.
Researcher Affiliation Collaboration Andi Han1, Bamdev Mishra2, Pratik Jawanpuria2, Junbin Gao1 1The University of Sydney, Australia 2Microsoft, India
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. Table 1 summarizes components, but it is not an algorithm.
Open Source Code Yes The code can be found at https://github.com/andyjm3/AI-vs-BW.
Open Datasets Yes Here, we test on a dataset included in the Mix Est package [30].
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts, or clear citations to predefined splits).
Hardware Specification Yes The experiments are conducted in Matlab using the Manopt toolbox [17] on a i5-10500 3.1GHz CPU processor.
Software Dependencies No The paper mentions 'Matlab' and 'Manopt toolbox [17]' but does not provide specific version numbers for these software components.
Experiment Setup Yes We set the batch size to be 50 and consider a decaying step size, with the best initialized step size shown in Figures 3(d)&(e).