Sequential Mode Estimation with Oracle Queries

Authors: Dhruti Shah, Tuhinangshu Choudhury, Nikhil Karamchandani, Aditya Gopalan5644-5651

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

Reproducibility Variable Result LLM Response
Research Type Experimental We report numerical simulation results that support our theoretical query complexity performance bounds.
Researcher Affiliation Academia 1Indian Institute of Technology, Bombay 2Indian Institute of Science, Bangalore
Pseudocode Yes Algorithm 1 Mode estimation algorithm under QM1; Algorithm 2 Mode estimation algorithm under QM2
Open Source Code No The paper does not provide any specific links or explicit statements about the availability of its source code.
Open Datasets Yes Real world dataset: As mentioned in the introduction, one of the applications of mode estimation is partial clustering. Via experiments on a real-world purchase data set (Leskovec and Krevl 2014), we were able to benchmark the performance of our proposed Algorithm 2 for pairwise queries...
Dataset Splits No The paper does not explicitly describe validation dataset splits, only mentioning training and testing implicitly or through a dataset citation.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as CPU or GPU models.
Software Dependencies No The paper does not list specific software dependencies with version numbers for reproducibility.
Experiment Setup Yes For both the QM1 and QM2 models, we simulate Algorithm 1 and Algorithm 2 for various synthetic distributions. We take k = 5120 and keep the difference p1 p2 = 0.208 constant for each distribution. For the other pi s we follow two different models: 1. Uniform distribution : The other pi s for i = 3....k are chosen such that each pi = 1 p1 p2 2. Geometric distribution : The other pi s are chosen such that p2, p3....pk form a decreasing geometric distribution which sums upto 1 p1. For each distribution we run the experiment 50 times and take an average to plot the query complexity. ... With a target confidence of 99%, our proposed algorithm terminates in 631k pairwise queries...