- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper investigates parameter sensitivity and adaptation under deployment perturbations in neural networks using linear canonical transform (LCT) token mixing. The authors analyze three transform coordinates and examine their sensitivity, parameter movement, and recoverability after mapping to analog in-memory computing (AIMC) hardware. A regularized local response score is introduced to select parameter subsets for restricted fine-tuning. The experiments suggest that parameter sensitivity does not necessarily correspond to compensatory capacity.
Critical strengths
The authors provide theoretical derivations for the LCT parameterization and conduct several experiments to investigate parameter sensitivity, movement, and restricted recovery.
Critical weaknesses
My main concern is the lack of a clear and focused contribution. The paper combines LCT parameterization, hardware perturbation analysis, sensitivity estimation, and restricted fine-tuning, but the connections between these components are not sufficiently explained. I find it difficult to understand what the paper is ultimately trying to achieve and to distinguish its methodological contributions from the various empirical observations. The overall presentation is confusing, and the paper fails to clearly establish what fundamental new insights or algorithmic contributions it provides.
The experimental evaluation is also rather limited, focusing on a specific LCT-based architecture. Moreover, the results show that most recoverable capacity lies outside the LCT parameter space, which raises further questions about the practical significance and generalizability of the proposed approach.
Overall, I believe the paper requires substantial restructuring to clarify its research objectives, technical contributions, and the connections between its theoretical analysis and experimental findings.
Questions for authors
See weaknesses above.
Thank you for the follow-up and the additional results. The responses have clarified several of my earlier concerns.
1. Corrected random controlsThe corrected results address my concern about the random controls. The response criteria still outperform the composition-matched controls in 20/24 comparisons under both matching schemes. Although some margins have decreased, I agree that the conclusion in Section 5.3 remains supported.
2. Comparison with the gradient baselineThe explanation of the CIFAR-10 real-quadrature result is helpful. However, the advantage over gradient-based selection is less clear in the other settings. On CIFAR-10 (imaginary), Qfull achieves 0.934 compared with 0.928 for the gradient baseline. On CIFAR-100 (imaginary), Qdiag achieves 0.583 compared with 0.584. These results are quite close, and I agree that the benefit is setting-dependent.
Finally, the additional depth and hardware experiments are useful, but the findings remain limited to LCT models under simulated AIMC conditions. I suggest keeping this scope explicit in the revised paper.