Transfer Learning in Multiple Hypothesis Testing

Round 1

Reviewer 1 Report

In this paper, the authors introduce an approach to transfer learning in multiple hypothesis testing. However, there are still some major issues that need to be addressed, as follows:

- The title of the paper should be revised with a capital letter at the beginning.

- The title format in some sections is inconsistently written.

- The abstract contains typos (e.g., "?") in line 5.

- The introduction is quite lengthy and needs to be more concise to provide information to the readers effectively.

- Figure 1 should be revised to include sub-figures for better representation.

Figure 5 needs to be revised with increased vertical spacing.

- Table 1 has a different font format, size, and doesn't adhere to journal formatting standards.

- There is a lack of discussion on the limitations of the work and potential directions for future research.

Minor editing of English language required

Author Response

see pdf

Author Response File: Author Response.pdf

Reviewer 2 Report

See attached report.

Comments for author File: Comments.pdf

No problems.

Author Response

see pdf

Author Response File: Author Response.pdf

Reviewer 3 Report

The paper needs Major revision. The main reasons are:

- too much non-scientific worlds: catapults, gamut, ...

- Bayes Factor method is very well known. The authors have to emphasize
their novelty contributions.

- CNN are mainly used in image processing.

- Better comprehensive captions for the figures

- No Conclusion section to clearly express the contributions of the paper

- Overall presentation of the paper and English language need improvements

Comments for author File: Comments.pdf

- Overall presentation of the paper and English language need improvements.

Author Response

see pdf

Author Response File: Author Response.pdf

Reviewer 4 Report

This is a very good article, but very dense and complex. it is very important for multiple tests. The examples are well chosen.

1-The abstract needs to be rewritten as it is a little too emphatic, not scientific enough and does not show the theoretical complexity of the article.

 2-In the introduction, some sentences are repetitions: lines 59-62 and 84-86, 65-68 and 80-91, ...The text needs to be re-arranged to avoid these repetitions.

 3-It is repeatedly pointed out (and used in the examples) that priors are often improper. The introduction should add (and the rest of the text revised to simplify it) a paragraph justifying this choice of improper distributions. How do formal rules lead to such distributions (line 95)?

 4-The presentation of Table 1 should be harmonized with the other tables and the recommendations to authors.

 5-In Appendix A and equation A1, the reviewer is not convinced (but without having redone the calculations himself) that exponentials are not missing from the denominator. References 8 and 9 do not detail the calculation either. The article should explain why these Beta distributions appear.

6-Appendix B should explain the roles played by the various CNN parameters.

7-In appendix E, explain why prior distributions are not assumed directly on tau and rho. Is the prior dependence between tau and rho troublesome?

The English is absolutely correct, with no typos or grammatical problems.

Author Response

see pdf

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

See attached report.

Comments for author File: Comments.pdf

It is a bit rough in places but generally okay.

Author Response

We thank Referee 2 for his/her valuable comments. We hope to have properly answered all of them. Please consider the attached PDF file.

Author Response File: Author Response.pdf

Reviewer 3 Report

This version is improved, but not yet all my recommendations of the first reviews are satisfied.

Major revision

- too much non-scientific worlds: catapults, gamut, ...

- Bayes Factor method is very well known. The authors have to emphasize
their novelty contributions.

- CNN are mainly used in image processing.

- Better comprehensive captions for the figures

- No Conclusion section to clearly express the contributions of the paper

- Overall presentation of the paper and English language need improvements

Many improvement, but still needs some minor corrections.

Author Response

We thank Referee 3 and we attach the answer to the points he/she raised.

Author Response File: Author Response.pdf

Round 3

Reviewer 2 Report

See attached.

Comments for author File: Comments.pdf

There are a few places where the language is hard to follow but it is generally good.