Manifold-valued Dirichlet Processes

Authors: Hyunwoo Kim, Jia Xu, Baba Vemuri, Vikas Singh

ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5. Experiments To evaluate the proposed model, we conduct a set of experiments on synthetic and real-world data.
Researcher Affiliation Academia University of Wisconsin-Madison, Madison, WI 53706, USA University of Florida, Gainesville, FL 32611, USA
Pseudocode Yes Algorithm 1 HMC algorithm for DP-MGLM on Riemannian manifolds
Open Source Code No The paper provides a project page URL (http://pages.cs.wisc.edu/~hwkim/projects/dp-mglm/) but does not explicitly state that source code is provided there, nor is it a direct link to a code repository like GitHub.
Open Datasets Yes We used the Lifespan database (Minear & Park, 2004), which contains 580 subjects with ages ranging from 18 93.
Dataset Splits No The paper mentions 'Train' and 'Test' in Table 1 and sample sizes ('Our sample size is 300') but does not specify the explicit percentages or counts for training, validation, and testing splits.
Hardware Specification No The paper does not specify any particular hardware used for running the experiments (e.g., specific CPU or GPU models, or cloud computing environments).
Software Dependencies No The paper does not mention any specific software or library names with version numbers (e.g., Python, PyTorch, TensorFlow, etc.) that were used.
Experiment Setup Yes We perform a few hundred realizations where the number of MCMC samples in each realization is 1000. We set the burn-in period to 100 epochs.