shapelets, factor analyzers

Discussed shapelets with MJ Vakili (NYU) who is looking at fitting large numbers of galaxies in SDSS and CFHT imaging. I encouraged him to look at building a probability density function for galaxy morphologies, which is a project I have wanted to do for years: For one, this is the prior pdf that is needed for weak lensing and other studies. For two, it should have complex non-trivial topological structure because of the viewing-angle dependencies of the observed two-dimensional morphologies.

In the morning, Fergus and I discussed the various ongoing projects. At one point in the discussion we marveled at the value of factor analyzers and the remarkable situation that they have never been used in astrophysics. If anyone knows an exception, I pay beer for first example. Factor analyzers might be great—or mixtures of them—for Vakili's project.


  1. Factor analysis could also be considered dictionary decomposition, right?

  2. Excellent! I have many comments on this project. as you know, but here are my current Top 4:
    1) Be sure to use polar shapelets for a compact representation of spiral arms!
    2) A stumbling block for shapelets in weak lensing is their inability to fit the cuspy inner part of the galaxies' sersic-like profile. I wondered whether one might stretch the image first and do better. Watch the noise though.
    3) Most people have not been inferring the appropriate number of shapelet coefficients to use from the data - this is a mistake, I believe.
    4) I hear on the grapevine that Galaxy Zoo may be contributing classified images to a Kaggle morphology challenge very soon. This would be a good thing to participate in!