large scale canonical correlation analysis with iterative least squares

Authors: Yichao Lu, Dean P. Foster

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experiments also show that L-CCA outperform other fast CCA approximation schemes on two real datasets.
Researcher Affiliation Collaboration Yichao Lu University of Pennsylvania yichaolu@wharton.upenn.edu Dean P. Foster Yahoo Labs, NYC dean@foster.net
Pseudocode Yes Algorithm 1 CCA via Iterative LS, Algorithm 2 LING, and Algorithm 3 L-CCA are presented in the paper.
Open Source Code No The paper does not provide an explicit statement or link for the release of source code for the described methodology.
Open Datasets Yes The dataset used is the full Wall Street Journal Part of Penn Tree Bank which consists of 1.17 million tokens and a vocabulary size of 43k [18].
Dataset Splits No The paper describes the datasets used and performance comparisons but does not explicitly provide specific train/validation/test dataset splits or cross-validation details needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running its experiments, only mentioning 'CPU time'.
Software Dependencies No The paper mentions 'matlab built-in CCA function' but does not specify version numbers for any software dependencies.
Experiment Setup Yes In the experiments we fix t1 = 5 and vary t2. In both experiments we fix kpc = 100... For RPCCA L-CCA G-CCA we try three different parameter set ups shown in table 1 and the 20 correlations are shown in figure 1.