Information-theoretic Bounds on Matrix Completion under Union of Subspaces Model
This work addresses subspace clustering under incomplete information, but it appears incremental as it extends existing results.
The authors tackled the problem of matrix completion when columns are grouped into subspaces, extending recent results and showing implications for subspace clustering with missing data.
In this short note we extend some of the recent results on matrix completion under the assumption that the columns of the matrix can be grouped (clustered) into subspaces (not necessarily disjoint or independent). This model deviates from the typical assumption prevalent in the literature dealing with compression and recovery for big-data applications. The results have a direct bearing on the problem of subspace clustering under missing or incomplete information.