- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes ESRA and DP-ESRA, which is the differentially private version of ESRA, to solve pairwise worst-case ratio analysis. The problem is solved by maximizing the minimum ratio of between-class to within-class scatter across class pairs. The proposed method, ESRA, uses entropic smoothing to obtain a closed-form polar-factor step without an inner solver. Its private extension, DP-ESRA, perturbs the matrices directly and uses the post-processing property of DP. The paper provides utility analyses with experiments on image datasets. The methodological contribution appears limited, and the motivation for combining entropic smoothing with differential privacy needs clearer justification.
Critical strengths
-
I think the problem formulation is interesting. Is the formulation of the pairwise worst-case ratio analysis novel? Using pairwise within-class scatter is reasonable when the class distributions have different variances. More discussion about the
-
The algorithm is simple and computationally attractive. ESRA replaces the inner problem with softmax-weighted gradient calculations, which yields a closed-form polar-factor update.
Critical weaknesses
-
The privacy extension provides very limited additional novelty. Using the standard Gaussian mechanism and the post-processing property of differential privacy is very standard in the differential privacy literature.
-
The theoretical analysis contains a gap between the utility and the algorithm. The utility guarantee assumes a global minimizer of the objective, but the proposed algorithm guarantees only stationarity.
Questions for authors
-
Is the proposed pairwise ratio analysis novel, or is it adopted from existing work? Please clarify the contributions of the formulation.
-
What technical contribution does DP-ESRA provide beyond applying the Gaussian mechanism and post-processing? Can the authors demonstrate the specific benefit of entropic smoothing compared with other solvers using the same privatized statistics?
-
Some related work shows that when the initial point lies within the basin of attraction, then the algorithm can converge to a global minimum. Can the authors use similar techniques to establish global convergence?
I want to thank the authors for a thorough rebuttal and answering my main questions.
The writing of the paper was improved but in my opinion it is still far from being clear. For instance, I appreciate the new main result at a glance which is a nice addition, but I think it is still far too technical to provide intuition to a first-time reader of the paper. In general, I think that adding some more intuitive explanations throughout the paper would further improve its readability.