- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper proposes a variational explanation for sparse gradient saliency maps in adversarially trained networks. For two-layer ReLU networks with TV and weight-decay regularization, it claims that empirical minimizers converge, under prescribed joint scaling, to population-risk minimizers that optimally balance total variation and the Barron seminorm. For perturbations, the resulting gradient penalty is interpreted as promoting sparsity. Validation includes synthetic and image-classification experiments measuring accuracy, robustness, gradient norms, and thresholded sparsity.
Critical strengths
The variational formulation offers a conceptually useful connection between the perturbation norm, the induced gradient penalty, and network complexity. This provides a principled framework for investigating how adversarial regularization affects saliency geometry, supported by relevant qualitative illustrations in two-layer networks.
Critical weaknesses
- Lemma A.5 applies a pointwise upper bound inside a Rademacher-weighted sum without handling negative signs (p. 18, lines 932–939). This invalidates the reduction used to derive the complexity estimate and leaves the required uniform empirical-TV concentration bound unestablished. Separately, Proposition 5.3 infers uniformly bounded weight decay from an upper bound on (p. 30, lines 1584–1586), although the centered empirical-risk term can be negative and offset increasing regularization. No suitable lower bound is supplied to justify this inference. These gaps affect both the convergence and compactness arguments underlying Theorem 1 and are decisive for my recommendation.
- Absolute-threshold sparsity can increase under uniform gradient shrinkage without any increase in relative concentration. Consequently, the reported quantitative metrics cannot establish concentration on fewer coordinates. Although the paper includes two-layer ReLU experiments and normalized qualitative visualizations, it lacks a scale-invariant quantitative concentration analysis and systematic tests of the prescribed joint scaling under conditions closely matching the theoretical assumptions (Section 6 and Appendix F). The connection between the proposed mechanism and the empirical phenomenon therefore remains insufficiently supported.
Questions for authors
- Can the authors provide a valid replacement for the signed-sum argument in Lemma A.5, or an alternative uniform empirical-TV concentration bound sufficient for Theorem 1?
- Additional evidence for the current claims: Do the sparsity trends persist under scale-invariant concentration metrics, and can the predicted behavior be demonstrated in a controlled two-layer ReLU setting following the joint scaling in Eq. (11)?
6 comments
Thank you for the revisions. The revised proofs appear to address the two specific gaps identified in my original review, and the Hoyer results and ablations substantially address the uniform-gradient-shrinkage concern. However, two substantive concerns remain.
1. Existence of empirical minimizers (p. 4).
Weight decay does not guarantee attainment when the output bias is unregularized. For example, consider uniform inputs on , independent balanced binary labels, and the clipped logistic loss
This satisfies the stated assumptions and has population-risk minimizer . On an all-positive sample, constant predictors have zero TV and weight decay, while their empirical loss approaches zero as . Every finite predictor has strictly positive loss, so the infimum is not attained. Please qualify the existence claim and clarify whether the result relies on eventual attainment or quasi-minimizers.
2. The requested joint-scaling experiment remains missing.
My original question asked for both scale-invariant metrics and a controlled two-layer experiment following Eq. (11). The response addresses only the first part. The new Hoyer results concern deep ResNets with fixed weight decay, while the two-layer experiments use isolated configurations and threshold-based sparsity measurements. The connection between the observed concentration and the theorem’s specific selection mechanism therefore remains indirect.
The revisions improve the manuscript, but these concerns about its formulation and central explanatory claim remain unresolved. I would need clearer justification or qualification of these claims, together with a direct response to the outstanding experimental question, before supporting acceptance.
Thanks for your reply.
1. Existence of empirical minimizers: This is a valid point since indeed we did not discuss existence in our paper, similar to [1] who also analyzed weight decay without bias regularization. Note that indeed our results apply to quasi-minimizers as long as their energies are sufficiently small, see Remark 3.2.
The reviewer's example is very insightful but not generic. In fact, whenever at least two different labels exist, existence of solutions is restored. In fact, since by Borel-Cantelli the probability of this example occuring infinitely often is zero. In fact, existence even without bias regularization can easily be proved under a slight strengthening of Assumption 1 that essentially asks as . This would be in conflict to the boundedness of the loss which is why we are currently working on removing the boundedness assumption altogether, just like in [1]. Then we can treat all the standard coercive loss functions like the logistic cross-entropy loss suggested by the reviewer, the square loss, zero-one loss, etc.
Here is a proof sketch for existence under the above coercivity assumption and for inputs in a bounded set :
- Take a minimizing sequence of parameters . Thanks to the weight decay, are bounded sequences and w.l.o.g. (after passing to a subsequence) we assume they converge.
- For bounded weights and inputs we have for some contant that only depends on those bounds. Hence, w.l.o.g. we can assume that the inner biases for and are bounded from below.
- Let be the indices of neurons for which the inner bias diverges. Again, w.l.o.g. we can assume that these limsups are limits. Then for large enough and we have and we can express the sequence of minimizing networks as
- There are two cases: If the sequence for is bounded, then (after passing to a subsequence) w.l.o.g. exists and converges uniformly on to a neural network with at most neurons (noting that affine functions on bounded can be represented as a ReLU neuron plus a constant). Otherwise, it holds that (again up to a subsequence) or which implies that for some fixed . Together, with the uniform Lipschitz continuity of (with Lipschitz constant just depending on the bounded parameters and ) we get that uniformly in . This contradicts the property of being a minimizing sequence since by the coercivity assumption the loss diverges.
2. The requested joint-scaling experiment remains missing: That is correct and we are still trying to figure out how to best design such an experiment. First, we would like to emphasize, however, that the scaling assumptions in (11) are standard assumptions for generalization bounds in statistical learning theory, see also our answer to Reviewer bqBK. Furthermore, the scaling is already extremely good and most likely close to sharp, compared to the naive scaling which ensures that every -ball around a training data point contains at least one other training data point with high probability. Here, is the feature dimension! Finally, finding an explicit solution to the limit problem is very hard which makes an experimental verification of the convergence to such explicit solution difficult. What we are planning to include in the next days is a evaluation of the Bayes risk and the total variation for solutions for different values of the sample size on the toy data set from Figure 2.
[1] Park, J., Pelakh, I., & Wojtowytsch, S. (2023). Minimum norm interpolation by perceptra: Explicit regularization and implicit bias. Advances in Neural Information Processing Systems, 36, 8714-8756.
We would like to thank the reviewer for their time and their careful review. We are happy that the reviewer finds our paper "clear and easy to follow" and acknowledges that it develops "a principled framework for investigating how adversarial regularization affects saliency geometry".
We are also very thankful that the reviewer correctly identified two mistakes in our proofs. We were able to fix both proofs and therefore restore the theoretical claims made in our paper under slightly stronger scaling assumptions.
Below we provide a point-to-point reply to the identified weaknesses and questions.
Weaknesses
Questions