- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In this paper, the authors consider learning linear forward operators from covariance matching. They theoretically analyze the identifiability of solutions, the stability of gradients, and the behavior of gradient flow.
Critical strengths
The strength of this paper is to theoretically show that multiple reference covariances can reduce the set of solutions to finitely many isolated solution under some assumption. Also, the authors show that gradient flow with a warm start stays close to the initial model, which support the stability of low-rank learning. I think such an idea of using multiple reference covariances is very relevant and important for inverse problems to mitigate the ill-posedness.
Critical weaknesses
The theoretical analysis require several assumptions, such a suitable warm start , and simultaneous diagonalization conditions on the reference covariances . However, I am not sure how these assumptions can be verified in practice, since a warm start and reference covariances may be unknown in practice. I might have misunderstood points, though.
Questions for authors
-
Does the warm start need to be close to the true forward operator ? If so, is there any practical way to check if is close to ?
-
How can we verify the simultaneous diagonalization conditions on the reference covariances in practice ? Could the authors provide some insight on how to obtain the reference covariances ?
-
This is a question out of interest. Could the author discuss the possible extension of the argument to the nonlinear forward models ? I think this paper is very relevent to ill-posded inverse problem, and inverse problem often involve nonlinear setting. I do not ask the authors to add details, but just a brief discussion on this possibility.