Simultaneous Preference and Metric Learning from Paired Comparisons

Authors: Austin Xu, Mark Davenport

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

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on synthetic and real-world datasets to exhibit the effectiveness of our algorithm. We demonstrate the effectiveness of our approach through experiments on both synthetic and real-world datasets.
Researcher Affiliation Academia Austin Xu Georgia Institute of Technology Atlanta, GA 30332 axu@gatech.edu Mark Davenport Georgia Institute of Technology Atlanta, GA 30332 mdav@gatech.edu
Pseudocode No The paper describes the estimation strategy and optimization problems mathematically, but does not include any explicit pseudocode or algorithm blocks.
Open Source Code Yes Code available at https://github.com/austinxu87/Ideal Point Metric
Open Datasets No The paper uses "synthetic and real-world datasets" including two internal "Ph D program admissions datasets from Georgia Tech School of Electrical and Computer Engineering" (Unranked Candidates and Ranked Candidates datasets). No concrete access information (link, DOI, formal citation) is provided for these datasets, nor are they described as publicly available.
Dataset Splits No The paper does not explicitly provide specific training, validation, or test dataset splits (e.g., percentages or sample counts) for its experiments. While it discusses general concepts like 'validation', it does not specify how its own datasets were partitioned.
Hardware Specification No The paper does not provide any specific hardware details such as GPU or CPU models, memory, or cloud instance types used for running the experiments.
Software Dependencies Yes The above formulation is a convex (semi-definite) program and can be solved by standard tools such as CVX [39, 40].
Experiment Setup Yes Regularization parameters: γ1 = 2, γ2 = 0.002, γ3 = 0.001, = 1. Regularization parameters: γ(0)1 = 2, γ(0)2 = 0.002, γ(0)3 = 0.0001, (0) = 1; γ(k)1 = 2 3, γ(k)3 = 7 1500, (k) = 1