A Randomized Algorithm for CCA
About
We present RandomizedCCA, a randomized algorithm for computing canonical analysis, suitable for large datasets stored either out of core or on a distributed file system. Accurate results can be obtained in as few as two data passes, which is relevant for distributed processing frameworks in which iteration is expensive (e.g., Hadoop). The strategy also provides an excellent initializer for standard iterative solutions.
Paul Mineiro, Nikos Karampatziakis• 2014
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Retrieval | Flickr30K | R@122.7 | 144 | |
| Image Search | Flickr8K | R@118.7 | 74 | |
| Image Annotation | Flickr8K | R@111.7 | 18 | |
| Image Annotation | Flickr30K | R@128.3 | 12 | |
| Canonical Correlation Analysis | XRMB (test) | Sum of Correlations104.5 | 7 | |
| Canonical Correlation Analysis | MNIST half matching (test) | Sum of Correlations44.5 | 6 |
Showing 6 of 6 rows