Estimating the distribution of Galaxy Morphologies on a continuous space
This work addresses the challenge of accurately representing galaxy morphologies for astronomers, but it is incremental as it applies existing methods to a new domain.
The authors tackled the problem of summarizing galaxy shapes without losing information by using dictionary learning and sparse coding to reduce high-dimensional shape data into a low-dimensional continuous vector space, enabling statistical inference through probability distribution and manifold estimation.
The incredible variety of galaxy shapes cannot be summarized by human defined discrete classes of shapes without causing a possibly large loss of information. Dictionary learning and sparse coding allow us to reduce the high dimensional space of shapes into a manageable low dimensional continuous vector space. Statistical inference can be done in the reduced space via probability distribution estimation and manifold estimation.