- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The authors consider Posterior Diffusion Sampling (PDS) and aim to quantify the effects of approximating the intractable conditional score when using this method to solve inverse problems. Using the Feynman-Kac formula, the authors analyze the bias introduced by the DPS approximation to understand which samples are under- or over-sampled. They also quantify the effects of heuristics such as early guidance-stopping and trajectory-dependent step size, which practitioners use to prevent instability in the numerical implementation of DPS.
Critical strengths
I think the paper's objective of quantifying the limitations of the heuristics behind DPS is important and deserves attention. An interesting result is the precise quantification of the discrepancy between the DPS-SDE and the true posterior via the Keynman-Kac formula (Theorem 1), which explains when DPS over- or under-samples the posterior and points to principled ways of designing paths with smaller bias (Theorem 2).
Critical weaknesses
I believe there is an issue with Theorem 2. Its proof uses Lemma 3 and 4: the former requires to be smooth, while the latter uses . However, in Theorem 2, the reward , which is not sufficiently smooth. If the authors can solve this issue, or convincingly explain why it does not arise, and the other reviewers have not identified any other technical issues with the paper, I'm willing to raise my scores.
As minor points regarding the presentation, I believe Theorem 2 deserves a more extensive discussion, which is currently missing. Also, the paper does not have a conclusion section.
Questions for authors
See weaknesses.
2 comments
The authors have solved my concern about the proof of Theorem 2. I raised my score accordingly.
Thank you for the careful reading and for identifying this gap. You are right: the smoothness assumptions of Lemmas 3 and 4 do not directly cover the norm reward. We have revised Theorem 2 to include a Feynman–Kac formula accounting for its nonsmoothness.
1. Smoothness of the reward (Lemmas 3 and 4).
The reward is not C2: the Hessian of the norm is singular on the constraint, so the lemmas do not apply directly. In the revised Theorem 2, the reaction coefficient uses the absolutely continuous part of the Hessian, while an additional Stieltjes integral accounts for the singular contribution:
ζ∫0T−t∗ηt∗+s,dΛs.
Here ζ is the DPS step-size hyperparameter, ηt is the reciprocal of the discretization step size, and Λ is a continuous nondecreasing process arising from the generalized Itô formula for the norm of the Tweedie residual along the OU path. For a scalar measurement, Λ is the local time of the residual at zero, as in Tanaka’s formula:
∣rτ∣=∣r0∣+∫0τsgn(rs),drs+Λτ.
The additional contribution is a Stieltjes integral against Λ, so the weight is well defined. The appendix proves the formula by smoothing the norm, applying Lemmas 3 and 4 to the smoothed reward, and passing to the limit. After guidance stops, the remaining step uses only the OU semigroup and does not require a C2 reward. Under the other stated assumptions, the revised theorem covers any C2 measurement operator A:Rd→RL whose Jacobian has full rank on the constraint manifold.
2. Discussion of Theorem 2.
The revised discussion interprets the formula in two stages. When guidance stops, the Feynman–Kac weight characterizes the bias accumulated relative to the annealed surrogate. Generation then continues without guidance, smoothing both the reward tilt and this bias. The stopping time and guidance strength can therefore be tuned to approximate a reward tilt at a chosen temperature, while the formula characterizes the remaining bias. We also connect this interpretation to Huang et al., who use early guidance stopping to recover variance comparable to the reward tilt in a Gaussian example.
3. Conclusion.
We added a Conclusion section summarizing the Feynman–Kac characterization of DPS bias, ELG as an alternative tilt with a simpler reaction term and empirical improvements (Section 4), and the tradeoff introduced by early guidance stopping (Theorem 2). It also identifies a direction for future work: evaluating ELG at scale, where the conditional covariance Σt must be estimated from the learned denoiser.