- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper presents a study on the impact of different prediction target, signal (x-), noise (\epsilon-), and velocity (v-) predictions, on the final performance of the diffusion model. The authors explain the performance gaps between these different targets through the interaction between the prediction-target geometry and finite model capacity. They present several theorems for the affine low-dimensional subspace, low-rank Gaussian prior, mixtures of low-rank Gaussians, which show that the clean prediction (x-prediction) remains in a low dimensional subspace but the noise and velocity predictions scale with the ambient dimension D. Based on this geometric characterization, the authors propose a time-dependent shortcut that directly carries the ambient component, leaving the core network to represent the signal. Their empirical evaluation support their theoretical findings.
Critical strengths
In my view, the main strengthen of the paper is the geometric characterization of the impact of different prediction targets. The authors provides a theoretical explanation on why different targets could lead to different performance outcomes, even though they lead to the same score function at optimum.
The shortcut proposal also seems to be a nice contribution that produces large performance improvement in the ImageNet test, without adding significant complexity in the learning algorithm.
Critical weaknesses
One main concern is that all theorems seem to be straightforward, given the assumptions made prior for each theorem. There are not enough discussions on these assumptions, such as how far they are from the practical scenarios, and how we should interpret the theoretical results when these assumptions are violated. My impression is that the theorems provide some nice results but only under the context of the given assumptions, and they may not explain the real performance issues observed in the diffusion models. I believe a more detailed discussions and analysis on these assumptions and the gaps between the assumptions and the real situations are needed.
Another concern is on the empirical evaluation. The experimental evaluation only occupies one page in the main text, and the validation does not seem to be comprehensive enough to support all their findings.
Questions for authors
As already discussed in the weaknesses section, my main concern is on the assumptions that support the theorems. Can these assumptions been weakened, and be made closer to the practical scenarios? The theorems seem to be straightforward given these assumptions, so do these theorems really support what the authors want to claim on the impact of different prediction targets, or they are some simple consequences of the assumptions? What are the technical novelties in the proofs of these theorems on top of the assumptions made?
2 comments
Thank you again for your time and thoughtful feedback. As the author–reviewer discussion period draws to a close, we would like to ask whether our responses have addressed your concerns and whether you have any further questions we could clarify.
Author Response
We thank the reviewer for the constructive feedback. We have uploaded a revised manuscript, with changes highlighted in blue. All figure, table, equation, and section references below refer to this revision.
Weakness 1 [Assumptions and practical relevance]
Spatial, semantic, and temporal redundancy in images and videos motivates our structured signal models, whereas injected Gaussian noise spans the ambient space.
Our analysis extends beyond exact subspaces. Theorem 1 allows arbitrary distributions on an affine subspace, Theorem 3 considers low-rank Gaussian mixtures, and Theorem 6 addresses smooth manifold unions with off-manifold perturbations. These results show how geometric separation can persist for more complex structures under the stated conditions. The target relationships (Eq. 14) hold for arbitrary finite-second-moment data distributions; the separation and approximation advantages depend on the data structure and need not persist when that structure is absent.
Our analysis also provides a theoretical perspective on existing architectural designs. RAE-based models benefit from wider diffusion heads (Zheng et al., 2026), U-Nets use multiscale skip connections (Ho et al., 2020), and EDM has an input-to-output skip (Karras et al., 2022). Our geometric analysis helps explain why capacity and input pathways matter: they affect which target components the core must represent. In particular, the target-matched shortcut handles the ambient component outside the core.
Weakness 2 [Empirical evaluation]
Our experiments test the approximation predictions and examine their relevance to learning. In Figure 1, clean-prediction error becomes negligible once the signal fits, whereas noise/velocity errors grow with ambient dimension and fall with output rank. Figure 2 contrasts a persistent finite-budget gap at D=512 with slower but successful direct-v learning at D=32. Figure 5 shows improved Gaussian-mixture recovery with shortcuts.
Appendix D.3 (Table 3) further validates the predicted approximation behavior: direct v-prediction exhibits increasing error with ambient dimension, EDM reduces but does not eliminate this error, while both fixed and learned shortcuts achieve nearly zero approximation error.
New sampling comparisons (Appendix F.3, Figures 6–8, pp.34–36). We compare direct prediction, EDM-style preconditioning, and fixed/learned shortcuts for all three targets. At D=512, both shortcuts recover clearer projected spirals than direct ε/v-prediction.
New coefficient analysis (Figure 3, p.10) gives mean relative coefficient errors of 4.32% (ImageNet) and 0.81% (Swiss roll) on the uniform evaluation grid for t<0.95 against −1/d(t), d(t)=max(1−t,0.05). The agreement supports our interpretation that the input branch takes on the ambient component predicted by the theory (Appendices I.2/I.5).
New v-EDM comparison (Table 2, p.9). We adapt EDM preconditioning to v-prediction (Appendix D.2) under the same JiT-B/16 configuration (200 epochs). ImageNet 256×256 results are:
These results support our architectural interpretation: explicitly handling the input-dependent component can substantially improve v-prediction performance.
Questions for Authors [Theoretical significance and technical contributions]
The relaxation of assumptions is addressed in Weakness 1. Our contribution goes beyond geometric differences by quantifying their approximation consequences. Theorem 2 optimizes each target's output representation independently and shows that approximation gaps can persist after optimization error vanishes. Theorem 5 establishes how a target-matched shortcut removes the corresponding Gaussian approximation floor. Thus, score-equivalent targets need not place equivalent demands on the core.
The proofs derive target-specific spectral bounds and combine them with established convergence results (Theorem 2), prove Jacobian nondegeneracy for local nonlinear Gaussian-mixture learning (Theorem 4), and establish normal-energy bounds near smooth manifold unions (Theorem 6). These steps address approximation and learning, rather than only restating the assumed data geometry.
References