- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper studies the question what forward KL is achievable by different model classes (factorised, autoregressive and graph-Markov classes). The authors answer this question by using conducting a theoretical analysis. The authors then proceed to connect the results to the number of samples required for Boltzmann generators to reweight to the target density based on a result presented by Chatterjee and Diaconis.
Critical strengths
I enjoyed reading the beginning of the paper. Moreover, the paper is nicely structured until Section 3 and includes short proofs for their theorems.
Critical weaknesses
- Section 3 opens with a theorem without any context which suddenly mentions Potts chains which are neither explained nor introduced. Moreover, total correlation was only introduced in the context of fully factorized classes. Its not clear what the author intends to show with it neither does the subsequent paragraph on Ising chains (which is again neither introduced nor explained).
- Section 4 is just a theoretical result with an additional sentence. It is unclear to me what exactly it says and what the implications are. A bit more context would be helpful to make the paper more readable. Q: Does the result say that using annealed importance sampling requires less samples to do reweighting over the whole path compared to directly reweighting. If so, would this mean that the forward KL summed over the path is less then the forward KL from the initial proposal to the target?
- The theorems in this work are textbook identities presented as new contributions. None of the prior work is cited properly.
- The experiments are very small scale. It would be good for the authors to demonstrate the usefulness of their theory on some real-world applications.
After section 2, the paper appears to me as a collection of theorems without much context. Its difficult to read and related works do not seem to be credited appropriately. The paper needs significant work to be accepted at a venue such as ICLR.
Questions for authors
- Which modern Boltzmann-generator papers lie within the model classes discussed in this work?
See weaknesses for further questions
Response to Reviewer kmLd
Thank you for the detailed and constructive reading. We have revised the manuscript to address each of your points.
1. Context and definitions in Section 3 (Potts/Ising chains and total correlation). Total correlation TCS(μ) is now formally defined for any partition in Proposition 2(a) before Section 3 uses it. Section 3 opens with the shared mechanism across all three conditional-independence classes (Equation 1: the information each site carries about past coordinates omitted from its parent set), followed by one extensivity theorem for all classes (Theorem 4). When introducing the 1D m-state Potts chain (whose m=2 case is the zero-field Ising chain), we write out its distribution explicitly and explain why Theorem 4 is an equality there: single-site marginals are uniform and the chain is Markov, so TC(μL)=(L−1)Iμ(x1;x2), the number of bonds times the per-bond mutual information.
2. Section 4 and your question on Annealed Importance Sampling (AIS). Yes, your intuition is exact, and Section 4 (Proposition 8) now spells out this trade-off. Along a K-stage geometric path with exact stage-wise draws, the summed forward KL across stages is J(μ,q)/(2K)+O(K−2), which can be made far smaller than the one-shot D(μ∥q) by adding stages; accordingly, AIS avoids the exponential sample-size growth of direct reweighting. The work does not disappear, however: it moves into the stage transitions. Proposition 8 shows that total transition work W=Kn satisfies W≥J(μ,q)/ϵ2≥ΦQ(μ)/ϵ2 and approaches J/ϵ2 once K≫J. Thus an extensive floor ΦQ=Ω(N) sets one-shot reweighting at eΩ(N) draws while making annealed work linear in ΦQ. On an N=512 Ising chain, one-shot reweighting from the product proposal needs eΦ≈1072.7 draws, whereas AIS needs 1.9×105 transitions (Figure 6).
3. Credit to prior work. We agree and have revised Sections 2 and 7 accordingly. Proposition 2 presents the factorised, autoregressive, and graph-Markov identities as classical (Watanabe, 1960; Csiszár, 1975; Chow & Liu, 1968; Lauritzen, 1996). Section 7 credits Schneidman et al. (2003) for connected information, Erb & Ay (2004) and Lau & Grassberger (2013) for Ising multi-information, Neal (2001), Crooks (2007), and Grosse et al. (2013) for AIS variance and thermodynamic length, and Chatterjee & Diaconis (2018) and Sanz-Alonso (2018) for importance-sampling complexity, alongside lattice-scaling studies. Our new results (Theorem 5, Corollary 6, Proposition 7, and Proposition 10 on local receptive fields and diffusion samplers) are listed separately in Section 1.
4. Larger scale and real-world applications. The revision expands the experiments across three domains:
5. Which modern Boltzmann generators lie in these classes (Table 1). Particle-wise maps (Gabrié et al., 2022) lie in Qprod; VANs with reach shorter than the lattice (Wu et al., 2019) and hierarchical AR nets (Białas et al., 2022) lie in QAR/QG; convolutional couplings (Albergo et al., 2021; Kanwar et al., 2020), fixed-neighbour materials GNNs (Schebek et al., 2026), and convolutional lattice diffusion samplers (Wang et al., 2024; Tan et al., 2026) lie in Qloc(R) (R=Kr) and obey Theorem 5; while full-context flow-matching/transformer BGs (TBG, SBG, Prose; Klein & Noé, 2024; Tan et al., 2025a,b) and global-score diffusion samplers (PIS, DDS, iDEM) are universal, with zero structural floor.
We hope these revisions address all of your questions and are happy to discuss further.