Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Multitask Generalized Eigenvalue Program
Authors: Boyu Wang, Joelle Pineau, Borja Balle
AAAI 2016 | Venue PDF | LLM Run Details | Input Tokens: 15,582 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,391 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| 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 EMAIL, EMAIL Borja Balle Department of Mathematics and Statistics Lancaster University, Lancaster, UK EMAIL |
| 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. |