- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes targeted denoiser training using samples from Gaussian-restrained target distributions. Matching the restraint width to a diffusion time and constructing posterior-initialized bridges preserves the ordinary unconditional score or velocity regression target while changing training coverage. The method supports one-shot refinement by combining a pretrained high-noise model with a refined low-noise model, and Gibbs sampling when only the low-noise model is available. Experiments cover the Muller-Brown potential, explicit-solvent alanine dipeptide, and latent-space CLN025.
Critical strengths
-
The posterior-matched bridge is a useful construction for concentrating training on underrepresented regions while preserving the population denoising target. The conditional-regression argument in Theorem 1 and Appendix A is convincing under exact posterior sampling. The linear-CV construction and application to implicit molecular marginals are particularly useful when an explicit marginal energy is unavailable. The contribution lies in turning these probability identities into a practical training procedure.
-
The one-shot refinement experiments provide encouraging evidence at matched training-update budgets and without additional MD. Chignolin shares the representation and branch checkpoint, preserves the optimizer schedule, and uses the same sampling grid. Across four data budgets and both bridge times, the reported rare-state population error decreases. At the largest budget, t*=0.35 reduces relative error from 14.2% to 4.1%, while JS distance increases from 0.10875 to 0.11016 (Table 4). The consistent local improvement, together with the clear construction, makes me lean toward acceptance despite the attribution concerns below.
Critical weaknesses
-
The refinement comparison does not isolate the contribution of targeted bridge training. Refinement changes both the sampling distribution and the allocation of updates across noise levels. A continuation of ordinary denoising training restricted to [0,t*], from the same checkpoint and with the same stitched sampler, is missing. Averaging the matched bridge over its natural endpoint marginal recovers ordinary denoising training, making this an especially direct control. Without it, the advantage over simply prioritizing low-noise training remains unclear. Both rare-state and global metrics matter here, since the refined Chignolin models have higher global JS distances.
-
The from-scratch comparisons also change inference. In Muller-Brown, the baseline uses 400,000 independent 100-step reverse trajectories, while the proposed method uses 1,000 chains, 5,000 sweeps and 100 reverse steps per sweep to retain 401,000 correlated configurations. Counting each configuration separately, this is 12.5 times the total denoiser evaluations. The matched MD budget controls acquisition cost, but the contribution of the sampling protocol and its effective inference cost remain unresolved. The existing baseline could also use the same Gibbs sampler. Moreover, Algorithm 2's exactness is an invariance statement; convergence after the chosen burn-in needs empirical support.
Questions for authors
-
For one representative refinement setting, could you compare ordinary denoising continuation over [0,t*] from the same checkpoint, matching optimizer handling, coordinate preprocessing, update budget and stitched sampling? Please report the existing rare-state and global metrics.
-
On one representative Gibbs benchmark, how does the existing baseline checkpoint perform under the same Gibbs protocol? Please provide occupancy versus sweeps, burn-in sensitivity, and effective sample size together with sampling cost. This comparison can use the existing trained models.
-
For Chignolin, what are the rare-state frequencies in each training prefix, and how stable is the reference frequency across trajectory segments? The reported model-seed intervals do not capture uncertainty in the shared MD reference. Statistics from the existing trajectories would help interpret the reported probability accuracy.
2 comments
Response to Reviewer MfvY (2/2)
Q2. Matched inference, Gibbs behavior, and sampling cost
The from-scratch comparisons also change inference. In Muller-Brown, the baseline uses 400,000 independent 100-step reverse trajectories, while the proposed method uses 1,000 chains, 5,000 sweeps and 100 reverse steps per sweep to retain 401,000 correlated configurations. Counting each configuration separately, this is 12.5 times the total denoiser evaluations. The matched MD budget controls acquisition cost, but the contribution of the sampling protocol and its effective inference cost remain unresolved. The existing baseline could also use the same Gibbs sampler. Moreover, Algorithm 2's exactness is an invariance statement; convergence after the chosen burn-in needs empirical support.
On one representative Gibbs benchmark, how does the existing baseline checkpoint perform under the same Gibbs protocol? Please provide occupancy versus sweeps, burn-in sensitivity, and effective sample size together with sampling cost. This comparison can use the existing trained models.
A2.2 now includes matched inference controls for both Müller–Brown and ALDP, with the population comparisons added to Appendix E.1 (Table 1) and Appendix F.6 (Table 5), respectively. In Müller–Brown, the baseline and RDB use the same Gibbs protocol, and direct baseline sampling is also matched at denoiser evaluations per run. For ALDP, Appendix F.6 (Figure 7) reports occupancy versus sweeps under the matched Gibbs sampler, including the standard inference initialization control; the burn-in table in A2.2 compares sweeps 21–50, 31–50 and 41–50 across 20 training seeds.
To measure sampling efficiency, we additionally record 10,000 chains × 50 sweeps for each frozen seed-42 ALDP checkpoint. For the R5 occupancy averaged over sweeps 21–50, the variance-equivalent ESS is 48,385 for Restrained-MD-pair RDB and 55,048 for ordinary low-time continuation, from 300,000 retained states each. Both runs cost 50.49 million denoiser evaluations, including initialization and burn-in, and approximately 75.7 s per model on one RTX PRO 6000 Blackwell GPU. The ESS definition, Monte Carlo standard errors, and ESS per million evaluations are reported in A2.2.
Q3. Chignolin training prefixes and trajectory-segment variability
For Chignolin, what are the rare-state frequencies in each training prefix, and how stable is the reference frequency across trajectory segments? The reported model-seed intervals do not capture uncertainty in the shared MD reference. Statistics from the existing trajectories would help interpret the reported probability accuracy.
We computed misfold populations from the original Chignolin trajectory using the same state definition and excluding the initial 2 µs:
| Total trajectory budget | Training window | Observed misfold population |
|---|---|---|
| 3 µs | (2, 3] µs | 0.4720% |
| 4 µs | (2, 4] µs | 0.3930% |
| 5 µs | (2, 5] µs | 0.3473% |
| 6 µs | (2, 6] µs | 0.3060% |
| 7 µs | (2, 7] µs | 0.2938% |
| 12 µs | (2, 12] µs | 0.3607% |
| 17 µs | (2, 17] µs | 0.3707% |
| 22 µs | (2, 22] µs | 0.3747% |
In addition, A1 reports an entirely independent Chignolin evaluation reference. In the November 16 snapshot, three independently seeded trajectories provide 42.58 µs after burn-in (all-frame population 0.35968%). Using 20 complete 2 µs blocks (40 µs) yields 0.35975%, with approximate 95% block- interval [0.33611%, 0.38339%].
Figure 4(c) now marks the training population separately for each MD budget, alongside the independent reference and its 95% CI band. The independent-reference protocol is documented in Appendix G.2.
Response to Reviewer MfvY (1/2)
We thank the reviewer for the suggestions to disentangle targeted bridge training, low-time update allocation, and Gibbs inference, and to report reference uncertainty. All newly completed matched experiments are detailed in Reply to All Reviewers, A1–A2. We summarize their implications here and provide the requested Chignolin prefix statistics.
Q1. Matched ordinary low-time continuation
We agree that ordinary denoising continuation over [0,t⋆] is the most direct control. We implemented this control in Setting I for ALDP and Chignolin, matching checkpoints, additional updates, optimizer initialization, preprocessing, time interval, and sampling (A2.1; Appendices F.6 and G.7, Tables 4 and 9). We also include low-time continuation in the new image experiment, Notch (A3; Appendix H, Table 10). Across all three systems, the results demonstrate that RDB provides benefits beyond simply reallocating training to low diffusion times.