Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Sampling with Trusthworthy Constraints: A Variational Gradient Framework

Authors: Xingchao Liu, Xin Tong, Qiang Liu

NeurIPS 2021 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Various numerical experiments are conducted to demonstrate the ef๏ฌciency of our algorithms in trustworthy settings.
Researcher Affiliation Academia Xingchao Liu Department of Computer Science University of Texas at Austin EMAIL Xin T. Tong Department of Mathematics National University of Singapore EMAIL Qiang Liu Department of Computer Science University of Texas at Austin EMAIL
Pseudocode Yes See Algorithm 1, and the detailed version in Algorithm 3 in the appendix. ... See Algorithm 2 and more details in Algorithm 4 in Appendix.
Open Source Code Yes Code is available at https://github.com/gnobitab/ConstrainedSampling.
Open Datasets Yes We use the COMPAS dataset following the setting in Liu et al. (2020). ... We use the Adult Income dataset (Kohavi, 1996)
Dataset Splits No The paper mentions 'The hyper-parameters are determined by grid-search to reach the smallest constraint loss in each experiment', which implies some form of validation, but it does not specify explicit validation dataset splits (e.g., percentages, sample counts, or citations to predefined splits) to reproduce the data partitioning for validation.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions software components and methods (e.g., 'SVGD', 'RBF kernel', 'Langevin dynamics', 'Welling & Teh (2011)'), but it does not provide specific version numbers for any libraries, frameworks, or programming languages (e.g., 'Python 3.8', 'PyTorch 1.9').
Experiment Setup Yes The step size for the Lagrangian multiplier in primal-dual methods is chosen from {0.001, 0.01, 0.1, 1, 10, 100, 1000}. ... We adopt the same decaying step size as suggested in Welling & Teh (2011) for both SVGD and Langevin dynamics, where ht = h0(1.0 + t) 0.55 and h0 is a hyper-parameter.