Generalized Dictionary for Multitask Learning with Boosting

Authors: Boyu Wang, Joelle Pineau

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on both synthetic and benchmark real-world datasets confirm the effectiveness of the proposed approach for multitask learning.
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
Pseudocode Yes Algorithm 1 Generalized Dictionary for Multitask Learning Input: {S1, . . . , ST }, max Iter, the number of iterations K, the number of basis hypotheses M, regularization parameter µ
Open Source Code No The paper does not provide an explicit statement about releasing the source code for the described methodology or a direct link to a code repository.
Open Datasets Yes We now evaluate GDMTLB algorithm against several stateof-the-art algorithms on both synthetic and real-world datasets. Competitive methods include... London school data [Argyriou et al., 2007]; and two for classification: landmine data [Xue et al., 2007], and BCI Competition data2. 2http://www.bbci.de/competition/iv/.
Dataset Splits No The paper mentions 'In all experiments, the hyper-parameters (e.g., M, µ, different dictionary initializations) are selected by cross-validation.' and 'Each dataset is evaluated by using 10 randomly generated 50/50 splits of the data between training and test set'. It does not specify a separate, explicit validation dataset split.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions 'Regression tree is used as the weak learner of GDMTLB for regression, and logistic regression is used as the weak learner for classification.' but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup No The paper states 'In all experiments, the hyper-parameters (e.g., M, µ, different dictionary initializations) are selected by cross-validation.' but does not provide specific values for these or other training configurations in the main text.