Uploaded image for project: 'Mahout'
  1. Mahout
  2. MAHOUT-180

port Hadoop-ified Lanczos SVD implementation from decomposer



    • Type: New Feature
    • Status: Closed
    • Priority: Minor
    • Resolution: Fixed
    • Affects Version/s: 0.2
    • Fix Version/s: 0.3
    • Component/s: Math
    • Labels:


      I wrote up a hadoop version of the Lanczos algorithm for performing SVD on sparse matrices available at http://decomposer.googlecode.com/, which is Apache-licensed, and I'm willing to donate it. I'll have to port over the implementation to use Mahout vectors, or else add in these vectors as well.

      Current issues with the decomposer implementation include: if your matrix is really big, you need to re-normalize before decomposition: find the largest eigenvalue first, and divide all your rows by that value, then decompose, or else you'll blow over Double.MAX_VALUE once you've run too many iterations (the L^2 norm of intermediate vectors grows roughly as (largest-eigenvalue)^(num-eigenvalues-found-so-far), so losing precision on the lower end is better than blowing over MAX_VALUE). When this is ported to Mahout, we should add in the capability to do this automatically (run a couple iterations to find the largest eigenvalue, save that, then iterate while scaling vectors by 1/max_eigenvalue).


        1. MAHOUT-180.patch
          52 kB
          Jake Mannix
        2. MAHOUT-180.patch
          66 kB
          Jake Mannix
        3. MAHOUT-180.patch
          48 kB
          Jake Mannix
        4. MAHOUT-180.patch
          63 kB
          Jake Mannix
        5. MAHOUT-180.patch
          66 kB
          Jake Mannix

          Issue Links



              • Assignee:
                jake.mannix Jake Mannix
                jake.mannix Jake Mannix
              • Votes:
                0 Vote for this issue
                2 Start watching this issue


                • Created: