- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper presents a new practical and theoretical framework for identifying underlying grid (group) structure in measurements that have been scrambled in an unknown way. The proposed method relies on a combination of a recovery network and a loss estimation network together with a group-theoretic parameterization that captures underlying symmetries (in this case, the underlying grid) of latent signals/images. The method is demonstrated in a series of small-scale experiments, including generalized shot noise, Ising model estimation, MNIST pixel shuffling/bit scrambling, and learning the rotational symmetry from mouse visual cortex signals. Comparisons with LieGAN in the shot noise experiments show that the proposed method is more robust to varying configurations.
Critical strengths
- The paper tackles the highly challenging problem of recovering hidden symmetries (or, in this case, the underlying grid) from unstructured data, which hasn't received significant attention from the machine learning community
- Experiments, despite the small scale and high compute cost, are promising and can pave the way for new methods.
Critical weaknesses
My main concern with the paper is that it is quite hard to read/understand:
- The recovery and loss networks are not well defined - what are the learnable parameters of these networks? What is and in Figure 2? Similarly, the dataset is not defined anywhere, I guess it is some set of ?
- The experimental figures (3,4) can be significantly improved: what are the different MNIST images in 3.b - the output of which network? At what moment of training? The axes of subfigures in figure 4 need labeling - what are the different axes values?
- The abstract and conclusion mention a clear link with blind deconvolution, but the expression "blind deconvolution" is not present in the main sections 3, 4, and 5, and it's unclear what this link is?
- The experiments mention multiple times "signal recovery", but this concept is not explained anywhere in the main paper - its only mentioned in the introduction and experiments.
- I believe the notation is overly complicated, and many symbols can be removed, which would improve understanding. For example, are all the intermediate and representations crucial for understanding? what is the matrix ? Similarly, the different mathcal, lower/uppercase and bold notations should be simplified, for example figure 2.b alone uses , , , and .
- It is quite hard to understand how the data is defined on each experiment and how it fits with the model definition. For example, it's unclear what the data is and what the goal is in the generalized shot noise experiment.
- some mathematical symbols are not explained: what is in the total correlation and infomax losses? what is ?
- some acronyms are not explained, such as "JS"
- In section 6.2, why zero-padding if a central crop is used?
Questions for authors
Does eq. 1 assume that the mixing matrix is equivariant? If it has an unknown form, I wouldn't expect it to be necessarily equivariant
Dear Reviewer,
Thank you for your time, your constructive criticism, and for acknowledging the strengths of our methodology. Since the necessary revisions are substantial, we have decided to prepare our manuscript for another venue.
Based on your feedback, we have:
In addition, we will:
Regarding your questions:
Actually, we use random crops. In Figure 3, to focus on the digit itself, we tested the model's response on the center cropped digits, which could be the source of misunderstanding. We will make that clear in the caption.
Here, ρX denotes the true symmetry representation induced on the sample space which is also unknown, not the one estimated by the model, which is denoted by ρ^X. When the mixing matrix is invertible, it guarantees the existence of a translation symmetry representation ρX on the sample space. Our method works by discovering this representation, thereby adapting to the unknown mixing matrix. In summary, the only assumption here is the invertibility of the mixing matrix; there are no further constraining assumptions.
Best regards,
The Authors