- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1(−1)
Read review
Paper summary
The paper studies whether convex data augmentation methods, such as SMOTE, can generate synthetic distributions that approximate the true data distribution better than the original empirical samples. The authors provide theoretical convergence rates in Wasserstein distance, analyze the effect of neighborhood size and mixing bias, and compare the proposed approach with kernel smoothing using synthetic experiments.
Critical strengths
The paper addresses an interesting theoretical question about data augmentation. The authors provide upper and lower bounds for the convergence rates and analyze the trade-off between smoothing and bias. I also appreciate that the paper discusses some limitations of the theoretical results, particularly when using a finite number of synthetic samples.
Critical weaknesses
My main concern is the overall clarity and organization of the paper. I found the paper extremely difficult to read and follow, especially given the large number of theorems, propositions, and technical arguments. Although these results are mathematically related, I feel that the authors do not sufficiently explain how each result contributes to the main research question. As a result, the central contribution is difficult to identify, and the paper becomes unnecessarily complicated.
I also think the paper could be much better structured. The authors introduce several theoretical directions, including convergence rates, mixing bias, kernel smoothing, and manifold analysis, but the motivation for moving between these topics is not always clear. I believe the paper would benefit from a more focused presentation that emphasizes the most important results and explains their significance before introducing additional technical details.
Another concern is the experimental evaluation. The experiments are limited to synthetic distributions, and I am not convinced that the results demonstrate the practical usefulness of the analysis. In particular, it is unclear whether the improvements in Wasserstein distance translate into better performance on real-world machine learning tasks.
Moreover, some experiments use oracle tuning based on the true distribution, which is generally unavailable in practice. Although the authors also evaluate a theoretical tuning rule, I think a fully data-driven evaluation would provide stronger evidence.
I am also concerned about the gap between the theoretical setup and the experiments. The main convergence theorem assumes sample splitting, while the experiments use unsplit samples. In addition, the manifold experiments are not supported by an equivalent general convergence-rate theorem.
Finally, I could not find a public code repository in the provided manuscript, which makes independent reproduction of the experimental results more difficult, despite the detailed experimental descriptions in the appendix.
Questions for authors
-
Could the authors explain more clearly what the main theoretical contribution is and why all the additional theoretical results are necessary?
-
Could the authors provide a clearer connection between the different theorems and explain how each one supports the central claim?
-
Why are the experiments limited to synthetic distributions? Could the authors provide results on real-world datasets or downstream learning tasks?
-
How can the neighborhood size be tuned in practice without access to the true distribution?
-
Could the authors clarify how the theoretical guarantees apply to the unsplit sampling procedure used in the experiments?
-
Given Corollary 3.1, which shows that the improved convergence rate may not carry over to finite augmented training sets, how significant is the main result for practical data augmentation?
We thank the reviewer for reading the rebuttal and for raising the score. Each of the three remaining points has a concrete answer in the revision.
1. Downstream performance. We measure W1 because it controls downstream performance for every Lipschitz loss at once. By Corollary 3.2, a model trained on the synthetic distribution has excess risk at most a constant times LW1(ν^,μ0) for any loss that is L-Lipschitz in the features. So a 4–14% smaller W1 on the real data (Table 26) is a 4–14% smaller bound on the downstream loss for all such losses and models, whereas a classifier run would show one loss and one model. The ordering of K given by our theory is also the one observed for F1 on 21 imbalanced datasets by Kachan et al. (2025).
2. Theory–practice gap. We believe the revision closes this gap. The cross-fit generator of Section 2, which runs the split generator twice with the halves exchanged and averages, uses every point, has the proved rate, and is as simple to run as SMOTE. It is a practical method with a guarantee, and the split itself is only a device of the proofs. What remains unproved is the rate of standard SMOTE itself, which differs from the proved generator in that the neighbours of a point are searched among the other half of the sample, and which behaves identically in our runs: on the same samples with the same k, the exponents are within 0.023 and the levels within 11% of each other (Table 12). The manifold experiments, which were not covered by a theorem at submission, are now covered by Theorem H.1.
3. Finite augmented sets. Corollary 3.1 answers this exactly. With N synthetic points the error cannot fall below (n+N)−1/d, so a small augmented set keeps a better constant but not the rate, and the rate is kept when N grows faster than n. Oversampling to class parity, the typical use of SMOTE, gives N=(ρ−1)n for an imbalance ratio ρ, which is the case where the condition can hold. The real-data experiment is a finite augmented set of this kind, with ρ from 9 to 42 and a 4–14% gain. The rule for k and the threshold kd hold at any N.
Presentation. We take the point, and we have uploaded a restructured version rather than promising one. The main change is that the sharpest result is now stated in the main text, as part (iii) of Theorem A: with its own k, k-NN SMOTE attains the exponent eK=min[2/(d+2),2K/(d(K+1))] at every K, so that with Theorem B the exponent of local convex mixing is known exactly. Section 3 now contains Theorems A and B, their two corollaries and one paragraph of mechanism in words, and the technical discussion (the chaining argument below the sampling scale and the proof ideas) has moved to the new Appendix E.7. The manifold extension is stated in the main text as Theorem C. The abstract and the title of Theorem A now name the split form of the generator, and Section 6 says that the real-data gains are gains in the constant, outside the regime of the rate theorem. The results themselves do not change.
If any of the three points is still open after this reply, we would be glad to address it before the discussion closes.