- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper studies how to discover, certify and preserve conservation laws shared across gradient-flow environments, and design a workflow, combining MEND for discovery, a set of checks for certification, and CCA for preservation. The workflow is tested on a simple network, while the downstream evaluation using learned laws does not meet its overall success criterion.
Critical strengths
- The motivation and method are clear. The authors systematically analyze several failure cases in discovering and validating conservation laws and design checks to address them.
- The authors provides detailed ablation experiment and explaination for their workflow, and report both positive results and limitations.
Critical weaknesses
- The empirical validation of the certificate is limited by experiment scopes. The experiments use a very small network with known quadratic conservation laws and focus on predefined law-count boundaries. It will be better to show whether the certificate would be transferred to unknown law families, larger models, or candidates produced by other discovery methods.
- The practical value of certified laws seems not very much. The paper explains well why each test is needed to avoid false or task-local laws, but not why obtaining certified common laws is useful in practice. The only downstream use with learned laws, constraining Adam with CCA, fails its own evaluation criterion due to conditioning issues along the optimizer path, and the successful preservation experiment uses analytic laws in a separate attention setting.
Questions for authors
- What will happen on candidates produced by other conservation laws or discovery methods? Do the existing thresholds in Eq.15 keep reliable without retuning, and how sensitive are the certification decisions to these thresholds?
- Is there a concrete downstream setting in which learning and certifying common laws is useful when analytical laws are unavailable or difficult to derive? Beyond reducing conservation law drift, is there evidence of an optimization benefit from using the certified learned laws?