Testing Determinantal Point Processes

Authors: Khashayar Gatmiry, Maryam Aliakbarpour, Stefanie Jegelka

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Small-scale experiments in Appendix J validate the algorithm empirically.
Researcher Affiliation Academia Khashayar Gatmiry MIT CSAIL gatmiry@mit.edu Maryam Aliakbarpour Univ. of Massachusetts Amherst maryam.aliakbarpour@gmail.com Stefanie Jegelka MIT CSAIL stefje@mit.edu
Pseudocode Yes Algorithm 1 DPP-Tester
Open Source Code No The paper does not contain an explicit statement about releasing its source code or a link to a code repository.
Open Datasets No The paper refers to receiving "samples from an unknown distribution q" for its testing algorithm, but does not explicitly mention using a specific named, publicly available dataset or provide access information for any dataset used in its experiments.
Dataset Splits No The paper does not explicitly provide information about training, validation, or test dataset splits. Its focus is on the sample complexity for distribution testing, rather than traditional model training with data splits.
Hardware Specification No The paper does not provide any specific details regarding the hardware used for running its experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper does not provide specific details about the experimental setup, such as hyperparameter values, optimizer settings, or other system-level training configurations.