Hiring Under Uncertainty

Authors: Manish Purohit, Sreenivas Gollapudi, Manish Raghavan

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We test the performance of our algorithms for the HIRING WITH UNCERTAINTY problem in both the sequential and parallel offers setting via simulations. We generate simulated data sets as follows.
Researcher Affiliation Collaboration 1Department of Computer Science, Cornell University 2Google Research. Correspondence to: Manish Raghavan <manish@cs.cornell.edu>.
Pseudocode Yes Procedure 1 Approx Given Tree(T); Procedure 2 Parallel From Sequential(T); Procedure 3 Knapsack Finite Probes(p, v, s)
Open Source Code No The paper does not provide any statements or links indicating that the source code for their methodology is open-source or publicly available.
Open Datasets No The paper states: 'We generate simulated data sets as follows.' It describes the generation process but does not refer to a publicly available dataset with concrete access information (link, DOI, formal citation).
Dataset Splits No The paper describes generating simulated data for experiments but does not provide specific details on training, validation, or test dataset splits (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory, cloud resources).
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes The values for n = 100 candidates are chosen uniformly at random from [0, 1]. We consider three models to generate the probabilities: Negative correlation: Higher-value candidates are less likely to accept offers. We sample pi s according to a Beta distribution, with pi Beta(10(1 vi), 10vi). Positive correlation: Higher-value candidates are more likely to accept: pi Beta(10vi, 10(1 vi)). No correlation: pi Uniform[0, 1]. On each of these data sets, we consider the performance of our three algorithms each with k = 20.