- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work studies a conditional-variance estimator for diffusion regression, where the goal is to estimate the variance using samples from the diffusion model. After showing that small KL error (as typically established in the literature) does not guarantee small variance estimation error, the authors investigate the theoretical guarantee of a (clipped version of) typical pairwise variance estimator, and they further show that the rate is minimax optimal among a designed distribution class. A practical way to set the clipping radius is also studied with theoretical guarantees. Numerical studies on synthetic data are provided.
Critical strengths
- The proof is largely sound.
- The paper is based upon an existing variance estimator with theoretical results that achieve the minimax rate (by proving a lower bound).
Critical weaknesses
- The largest weakness to me is the one-dimensionality starting from Section 4.2. While all the content before can be applied to multivariate , it is not the case to select the common radius, where fixed anchors on the interval are used for interpolation. For multi-dimensional features, such interpolation becomes very hard. This is also the case in the experiment, which is based upon an one-dimensional .
- Besides, even with one-dimensional , the current experiment does not fully suggest the benefit of the common radius. Specifically, in Table 1, the Variance RMSE with common radius might not be advantageous over the unclipped version. However, from Theorem 1, an unbounded would yield a worse upper bound, for sure. While the authors admit this in the experiment, more discussion needs to be given.
Questions for authors
- Please address my two comments above. Also, for the one-dimensionality issue, is it possible to let be a hyper-parameter itself and perform some hyper-parameter tuning? (Might be left for future works)
- While (7) and (8) are based on existing works, the later time correction in (9) is added. The logic is clear: it is needed to guarantee un-biasedness. However, just as in classical estimation theory, unbiasedness does not guarantee the minimum MSE. Thus, is it possible to get around such a time-correction and obtain a smaller MSE?
- Suggestions on writing: Please discuss assumptions and interpret your theoretical results. For example, as far as I see, Assumption 2 is not standard in the literature. While it might be a direct consequence of statistical learning bounds, this must be stated explicitly to relate to existing assumptions. Also, the terms in Theorem 1 needs to be discussed. For example, suppose becomes large and given that all higher moments are bounded, there still remains the last term to grow unbounded. Why is that term, and is it due to the analysis technique or to the problem nature?