- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies latent diffusability through Fisher information (FI) and its dissipation rate (FIR) under Gaussian smoothing. It relates these quantities to the derivative of the population MMSE, establishes intrinsic-FI bounds under geometric encoders, and develops local FIR stability bounds involving dimensional compression, tangential distortion, encoder nonlinearity, and manifold curvature. Experiments on Gaussian toy distributions and image representations use trained diffusion models to estimate FI/FIR and examine their relationship with representation geometry and generation quality.
Critical strengths
The paper tries to address a theoretical question: how do changes in encoder geometry affect FI and FIR? In particular, the intrinsic-FI transformation bounds distinguish tangential metric distortion from variation in the volume Jacobian, while the local Gaussian-smoothed FIR bounds account for near-isometry, encoder nonlinearity, and manifold curvature. These results provide a more quantitative account of representation geometry than an informal appeal to “latent distortion.” I regard this geometric analysis as the paper’s principal strength and as potentially valuable independently of its practical estimation procedure.
Critical weaknesses
1. The empirical FIR estimates disagree substantially with the exact Gaussian benchmark.
In the dimension-varying experiment in Section 4.2, two standard Gaussian coordinates are embedded in dimensions, and the encoder preserves these coordinates while removing only zero coordinates. This setting changes ambient dimensionality without losing signal or introducing nonlinear distortion.
For this setting, Eqs. (39)–(42) give
and
At and , the exact normalized deviation is approximately , whereas the corresponding blue curve in Fig. 2(b) appears to be approximately . Both the panel’s ordinate and the accompanying text identify this quantity as .
Appendix C explains that these quantities are estimated using learned-score Jacobians. The discrepancy therefore raises a central calibration question: how accurately do these estimates recover the population quantities analyzed by the theory? Agreement with the decreasing trend of the loose upper bound does not resolve the disagreement with the exact value.
Until this discrepancy is explained, the empirical curves provide insufficient support for the proposed geometric interpretation. Their variation may reflect score-Jacobian estimation error or normalization differences as well as representation geometry.
2. The incremental diagnostic value of FI/FIR remains unclear.
The experiments compare FI/FIR curves and generation performance after diffusion models have already been trained. They do not establish whether these diagnostics can reliably inform encoder selection or design. Reliable pre-training estimation is explicitly left to future work. The current experiments therefore demonstrate retrospective associations, but do not establish that FI/FIR can guide representation selection before expensive diffusion training.
The comparisons also do not establish what FI/FIR reveals beyond latent dimensionality, scale, reconstruction quality, or spectral statistics. Although the paper uses similarly sized pretrained models and normalizes latents in the FFHQ experiments, these measures do not isolate the additional explanatory value of FI/FIR.
The geometric bounds are potentially informative, but the experiments have yet to establish a concrete decision or insight that these diagnostics enable beyond the simpler measurements already available. This limits the demonstrated practical significance of the framework.
Questions for authors
-
Calibration of Fig. 2(b): For , , , and , Eq. (42) gives , while Fig. 2(b) shows approximately . What accounts for this difference? Please report the underlying estimates of and , specify the normalization and noise parameterization used, and explain whether the same issue affects the other FI/FIR comparisons.
-
Incremental diagnostic value: What do FI/FIR reveal about representation quality that is not already explained by dimensionality, scale, reconstruction quality, or spectral statistics? Which existing results isolate this additional information, and what conclusions about encoder selection or design do those results support?
Summary of Changes in the Revised Manuscript
We thank all reviewers for their constructive feedback. We have uploaded a substantially revised manuscript, with changes marked in blue. The main revisions are summarized below.
We have also refined our claims to better reflect the scope of the theoretical guarantees and empirical evidence. We hope these revisions make the contributions and limitations of the work clearer and easier to assess.