Multitask Generalized Eigenvalue Program
Authors: Boyu Wang, Joelle Pineau, Borja Balle
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical evaluation with both synthetic and benchmark real world datasets validates the efficacy and efficiency of the proposed techniques, especially for grouped multitask GEPs. |
| Researcher Affiliation | Academia | Boyu Wang and Joelle Pineau School of Computer Science Mc Gill University, Montreal, Canada boyu.wang@mail.mcgill.ca, jpineau@cs.mcgill.ca Borja Balle Department of Mathematics and Statistics Lancaster University, Lancaster, UK b.deballepigem@lancaster.ac.uk |
| Pseudocode | Yes | Algorithm 1 MTGEP for Leading Eigenvector (MTGEP-L) ... Algorithm 2 Multitask Generalized Eigenvalue Program (MTGEP) |
| Open Source Code | No | No explicit statement or link providing access to the open-source code for the described methodology. |
| Open Datasets | Yes | the landmine dataset (Xue et al. 2007), and USPS and MNIST datasets (Kang, Grauman, and Sha 2011).", "One benchmark dataset, dataset IIa from BCI competition IV1 is used for performance evaluation. The dataset consists of EEG signals from 9 subjects who are instructed with visual cues to perform left hand, right hand, foot, and tongue motor imagery . In this study, only the EEG signals from the left hand and right hand motor imagery are used. 1http://www.bbci.de/competition/iv/. |
| Dataset Splits | Yes | In all experiments, the hyper-parameters (e.g., M, ρ) are selected by grid search and cross-validation.", "For each subject, the EEG signals consist of a training set and a test set, each containing 72 trials per EEG pattern. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory amounts) are provided for running the experiments. |
| Software Dependencies | No | No specific software dependencies with version numbers (e.g., library or solver names with versions) are provided. |
| Experiment Setup | No | The paper mentions that 'hyper-parameters (e.g., M, ρ) are selected by grid search and cross-validation,' but it does not provide the specific values for M, ρ, or other training configurations such as learning rates, optimizers, or epochs. |