Regret Ratio Minimization in Multi-Objective Submodular Function Maximization

Authors: Tasuku Soma, Yuichi Yoshida

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Using real and synthetic data, we empirically demonstrate that our methods achieve a small regret ratio.
Researcher Affiliation Collaboration Tasuku Soma The University of Tokyo tasuku soma@mist.i.u-tokyo.ac.jp Yuichi Yoshida National Institute of Informatics, and Preferred Infrastructure, Inc. yyoshida@nii.ac.jp
Pseudocode Yes Algorithm 1 Coordinate-wise maximum method; Algorithm 2 Polytope method
Open Source Code No The paper does not provide concrete access to source code for the described methodology.
Open Datasets Yes In our experiment, we used the Movie Lens 100K dataset, consisting of 100,000 ratings from 943 users on 1,682 movies (Grouplens 1998)
Dataset Splits No The paper mentions using specific datasets but does not provide explicit details about training, validation, or test splits. It directly describes using the Movie Lens 100K dataset and creating a synthetic instance for the budget allocation problem without specifying how data was partitioned for different phases.
Hardware Specification Yes We conducted experiments on a Linux server with an Intel Xeon E52690 (2.90 GHz) processor and 256 GB of main memory.
Software Dependencies Yes All the algorithms were implemented in C# and run using Mono 4.2.3.
Experiment Setup No The paper mentions specific settings like 'set λ = 0.1' and 'adopted the double greedy method', but these are specific parameter choices or algorithmic methods, not a comprehensive description of hyperparameters (e.g., learning rates, batch sizes, epochs) or detailed training configurations typically associated with an experimental setup.