- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a new algorithm for Difusion Posterior Sampling. Diffusion Posterior Sampling refers to using Diffusion models for solving Bayesian inverse problems. Usually, diffusion posterior sampling ALGORITHM does not exactly model the true posterior. But this paper suggests that, if there are transition kernels (for Forward and Reverse Diffusion SDE of Eq. (9)) for the tilted transport process, we can sample from the true posterior by appling such transition kernels repeatedly. But in reality, kernel operations involve intractable integrals, so this paper rather repeats forward and reverse diffusion SAMPLING processes. For a toy problem (section 4.1), sampling can be performed analytically, but in a practical imaging problem (section 4.2), sampling is performed using a repeating sequence of (refining measurement consistency, forward diffusion, DDIM denoising). In both experiments, the proposed algorithms showed better quality of outputs.
Critical strengths
I believe the proofs and the theoretical claims are logically right, despite concerns of their usefulness.
Critical weaknesses
One weakness is that the aforementioned "kernel operation" cannot be employed in practical scenarios. Since integrating over y is actually intractable and the process relies on calculating only a single sample, the actual algorithm differs significantly from Equation (10). While Algorithm 1—designed for a toy problem where an analytical calculation of is feasible—fares somewhat better, Algorithm 2 simplifies to a process of calculating the loss term (likelihood or measurement consistency) via gradient descent, adding noise, and then denoising using DDIM; such methods have already been explored in prior research and I see no real novelty here. Another major weakness is that the Algorithm 2 involves running a nested loop after the initial DPS process, which inevitably incurs a significant runtime penalty. Numerous studies have been proposed to reduce the runtime of DPS, and this method is expected to be considerably slower than those alternatives (though this was not explicitly reported in the paper).
Questions for authors
- Could you please report runtimes of your algorithms?
- Why do you think Theorems 2 and 3 are useful, even though they are using 'kernel' forms? Can you insist similar ones when we use just one sample y, rather than the 'distributions' on y?
- In which kinds of practical inverse problems your algorithm is useful?
We thank the review for his/her time and efforts.
Q1: Image experiments run a modified algorithm (DDIM, gradient steps, no MH). PSNR/SSIM/LPIPS show better reconstructions, not accurate posterior sampling.
Q2: The finite-step bound relies on square-integrability not shown to follow from Assumption 1, and an approximate MH ratio does not give exact detailed balance.
Q3:What conditions ensure the square-integrability required in Appendix C.7? Can this be proved under Assumption 1, or are additional assumptions needed?
Q4:For super-resolution, which is linear, what is T∗, and why not use the exact kernel?
Q5: For nonlinear problems, what distribution does the chain you actually run (Euler step, no MH) converge to, and how does its bias depend on t?