- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies randomized smoothing when noisy samples are filtered by a fixed feasibility or confidence rule before their labels are aggregated. It shows that applying the ordinary Gaussian robustness formula to label probabilities conditional on retention can produce invalid certificates. The authors characterize when conditioning preserves Gaussian probability and divergence bounds, and connect these properties to the retention probability and conditional covariance. They also prove that conditional label probabilities alone cannot give a positive universal radius over arbitrary filters. Two valid certification routes are developed: one using joint retention-and-label probabilities, and another using a uniform covariance bound. Analytic examples and image-classification experiments illustrate both the failure of the naive substitution and improvements in certification for a fixed filtered predictor.
Critical strengths
-
The paper identifies a certification error and makes it precise through explicit counterexamples and an impossibility result. The released-model investigation also shows that the issue can occur in an existing implementation. The joint-mass correction preserves the filtered predictor and has a finite sample procedure.
-
The distinction between Gaussian event comparisons and divergence bounds is useful. In particular, the nonconvex example shows that conditioning can preserve useful divergence bounds even when the ordinary Gaussian probability comparison fails. The covariance-based analysis then explains how a valid conditional certificate can still be obtained.
Critical weaknesses
-
My main concern is the practicality of the stronger geometric certificate. Proposition 9 requires a verified covariance bound throughout a neighborhood, which is a substantial additional input for a learned confidence or feasibility filter. The positive image experiment uses a specially structured projected-band filter for which this bound follows analytically. It remains unclear which practically motivated filters can obtain a useful bound without substantial additional verification. Moreover, unfiltered smoothing remains stronger even with matched model calls (Table 9), while the band filter is not tied to an independent feasibility requirement. The experiment therefore demonstrates better certification of a particular filtered predictor, but leaves its broader practical value unclear.
-
I found the exposition difficult to follow, particularly the organization of Sections 3 and 4. The paper moves between event comparisons, divergence bounds, an exact CDF criterion, and a local covariance diagnostic before giving operation on page 7. These results serve different purposes, and the reader has to reconstruct which ones diagnose failure and which ones yield a usable certificate. The main text should also distinguish the new insights from the applications of existing tools more directly, using the comparison already provided in Appendix J.
Questions for authors
-
Beyond the projected-band construction, which practically motivated nonconvex filters can currently obtain a useful, verified covariance bound for Proposition 9? Please explain what is needed to determine and , including the computational effort.
-
What independent task or feasibility requirement motivates retaining the filter in the positive image experiment? Given that unfiltered smoothing performs better at matched model calls, a clearer account of when filtering is necessary or otherwise valuable would strengthen the practical significance. I am not asking that filtering always outperform ordinary smoothing, but that the example explain why preserving this filtered predictor is a useful objective.
We structure our response into 1) Changes we made to address reviewer concers and 2) answering the questions.
Addressing Weaknesses
Adding covariance verification for nonconvex box unions
We added a verifier for explicit nonconvex box unions in Section 4, Table 1, and Appendix J, with independent products in Appendix J.1. Answer 1 below explains its inputs and computational effort. Answer 2 separates the image experiment's certificate comparison from the trained-controller task requirement.
Improving clarity, organization, and attribution
We clarified the roles of the results in Sections 3-4. The projected-CDF criterion characterizes event control, and local covariance diagnoses divergence behavior. Certification uses either joint masses or a covariance bound verified throughout the required neighborhood. Section 4 now states the verifier inputs and procedure alongside the examples. Moreover, Section 1 and Appendix H explicitly distinguish the conditional-law results from the convex comparison, rejection-based certification, and categorical Rényi threshold inherited from prior work.
Q&A
Question 1
The verified family comprises explicit unions of boxes, including L-shaped workspaces, rectangular obstacle exclusions, and unequal corridors. The verifier takes the set, nominal center, noise scale, and a chosen verification radius R. Rational cells cover the entire center ball. Outward Gaussian moment enclosures prove positive retention and bound covariance throughout every cell. The largest verified eigenvalue bound, divided by σ2, gives Λ.
For a candidate radius r at Rényi order α, choose R≥αr and check Proposition 8, the revised numbering of Proposition 9. Increasing R can increase both the verification cost and Λ. The two-dimensional examples each use 4,096 cells and take at most 0.132 seconds in one CPU process, excluding imports. An exact product constraining all 32 coordinates takes 1.92 seconds. Work is additive across independent blocks at fixed block dimension. Coupled constraints require joint verification. This gives a tractable geometric family, while verification of general neural confidence regions remains open.
Question 2
The band filter has no independent CIFAR feasibility requirement. We clarified in Section 5 that it makes the covariance premise analytically checkable and permits a controlled comparison of certificates for one fixed filtered predictor. Unfiltered smoothing remains stronger at matched model calls. The supported conclusion is improved certification of that filtered predictor.
The added control studies address a separate task requirement. Retention enforces zero next-step native cost for trained actors, at the observed expense of progress and possible abstention (Appendix K). These studies use joint-event certification and an offline restored-state simulator oracle.