- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
ZoAQ adaptively allocates zeroth-order queries by reusing historical evaluations and testing the cosine similarity between a candidate gradient estimate and historical momentum. The paper analyzes estimation error, momentum tracking, and conditional descent, with experiments on synthetic optimization, black-box attacks, and language-model fine-tuning.
Critical strengths
-
The controller is straightforward to implement. Its acceptance test requires no additional function evaluations, and newly acquired samples contribute to the current estimate.
-
The analysis explicitly considers the trade-off between estimation error and staleness under historical reuse. Experiments cover several application settings.
Critical weaknesses
-
The claimed advantage regarding validation-query overhead is poorly supported.Bollapragada & Wild (2023, §2.1) and Bollapragada et al. (2024, §2.3) already allow variance estimation using a subset of the current samples. These baselines do not inherently incur "validation-only" query costs. Furthermore, Appendix F.3 treats the base-point evaluation in one-sided differences strictly as statistical overhead, even though it actively contributes to gradient estimation and Appendix G.1 assigns the same cost across all compared methods.
-
The momentum-tracking assumption is restrictive and empirically unverified.Theorems 5.3 and E.3 require: In fact, consider along the noiseless gradient-descent trajectory , with true gradient . An EMA , initialized at zero, satisfies , so its relative tracking error approaches . Bias correction does not change this limit. Thus, the required tracking condition need not hold even along such a simple deterministic trajectory.
-
Theoretical guarantees do not cover the actual implementation. Algorithm 1 accepts a candidate at even when the test fails. Theorems 5.3 and E.3 instead require a sufficiently large cap, thereby excluding this fallback. Corollary D.4 accounts for query costs but does not control the frequency or cumulative optimization effect of failed-test updates.
Questions for authors
-
Which queries in the cited adaptive sampling methods are used exclusively for validation? How is the overhead attribution in F.3 consistent with the common accounting in G.1?
-
Can the authors report momentum’s relative error against the true gradient and the fraction of iterations satisfying the tracking condition on synthetic objectives?
-
How frequently does the algorithm hit and update on a failed test? Can the convergence theory be extended to account for these fallback steps and the actual R-AdaZO update?