- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This manuscript proposes a method for an interesting setup of the sampling problem, that assuming the landscape (e.g., a potential function) is not known but given trajectory data derived from the overdamped Langevin equation driven by the potential function, how one could leverage the trajectory data to perform additional sampling task. The theoretical core involves (1) the identification of the weight function with respect to the invariant measure (i.e., density ratio) evolves the Kolmogorov Backward Equation (KBE), cleverly leveraging the reversibility condition of the process, (2) use the standard Koopman spectral analysis for performing eigen-analysis for making prediction, and (3) to generate new samples, using the property that a Kullback-Leibler divergence-driven Wasserstein gradient flow and the forward diffusion share the same time-dependent marginal distribution to enable a relaxation and flow-based model to transport samples from an a priori defined prior distribution.
Critical strengths
-
The setup of the problem is interesting and definitely relevant to more physical sciences-driven applications, such as molecular dynamics.
- The setup carefully dissociates the generation of the "data" (trajectories) from the sampling algorithm. This is relevant in practice. Most generative modeling-based sampling methods require in-loop evaluation of the potential function; for complex systems, such an intrusive approach is time-consuming and could waste compute in repetitively sampling the same region in the state space.
-
The theoretical core linking standard results - the connection between KBE and the density ratio evolution under the reversibility condition and approximate Koodman analysis - together is clever and insightful from the perspective of stochastic processes. Turning this connection to explicit flow-based particle transport with error analysis is useful.
Critical weaknesses
- Despite the theoretical clarity, the reviewer remains skeptical about the practical aspects of the proposed methods, especially in well-separated multimodal settings.
-
The basic idea is to estimate the velocity field of the effective KL-Wasserstein flow from the trajectory data. For multimodal distributions, obtaining representative stationary data from trajectories can require simulation times comparable to or longer than the characteristic inter-basin transition times. Even with stationary sampling, the probability of observing the transition regions can become exponentially small as mode separation or barrier height increases. It is hard for the reviewer to believe that this method can accurately resolve rare-event-driven relaxation under practical data and computational budgets, and such fundamental limitations were acknowledged but not adequately resolved or quantified in the manuscript.
-
The reviewer tried to use the provided codebase to perform the following, idealized problems, supplying independent exact target samples for spectral estimation to give the method favorable training coverage. The reviewer invites the authors to consider these analytically tractable problems to address the limitation of their methods.
- [Mode discovery.] Consider , Gaussian mixture target with density and assume initial . This is to mimic that the Langevin dynamics has already discovered some local mode at , and the question we ask is if the method can reasonably populate the other mode at by transporting particles initially concentrated around .
- [Weight equilibration.] Again consider the Gaussian mixture target with density , but now with an initial mixture target with density . The question we ask is if the method can reasonably recover the target population weights of these two modes, which encode their free-energy difference in physical sciences.
With the limited review time, the reviewer could run the code, but the results were substantially inaccurate in the tested configurations. For example, in the discovery problem, the estimated spectral gap was approximately times the reference value, and no inter-basin crossings were detected even at ten times the reference mode-to-mode mean first-passage time (a recent paper provided the analytical formula based on mean first-passage time analysis.) In the equilibration problem, a few crossings occurred, but the left-basin fraction remained approximately 49%, rather than the target 90.9%, even at ten reference relaxation times. Particle collapse was also observed. Enforcing the constant eigenfunction exactly did not resolve these failures. These tests used the S regime; long-horizon integration used a stiff solver with tolerance checks and an early-time comparison against the supplied RK4 implementation. The reviewer cannot claim that the tested dictionary and configuration were optimally tuned.
-
-
Theoretically, such a rare event-driven transition can require extremely long time.
- Because the exact KL-Wasserstein gradient flow tracks the time-dependent marginal distribution of the diffusion process, the resulting particle dynamics must transport samples at the corresponding timescale. The reviewer questions whether accurate numerical particle transport across fast intra-basin relaxation and slow inter-basin redistribution can be achieved at practical computational cost without problem-specific adaptation. The long physical timescale alone does not establish that numerical integration must be prohibitively expensive.
- An additional problem is that the estimated spectral gap could be way off for these systems.
- Numerically, accurately estimating the eigenpairs by projecting onto a finite set of a priori selected basis functions is notoriously difficult and sensitive in high dimensions. On the one hand there is finite-sample spectral estimation error. On the other hand, for well-separated metastable basins, the first nonconstant eigenfunction is approximately constant within each basin, connected by a narrow transition layer near the separating barrier. It is difficult for the reviewer to believe that the chosen radial basis functions - furthermore, not even with fully data-driven basis functions (meaning, solving the inverse of the full Gram matrix, : number of samples), since their centers are placed on fixed spatial grids - can reliably resolve and its derivatives in this regime without a demonstrated choice of grid space, bandwidth, and regularization.
-
Questions for authors
-
Could the authors discuss the limitations of the method, particularly for the rare-event-driven processes described above? Clarifying the regime in which accurate spectral estimation and particle transport are practically achievable, and diagnostics that can signal unreliable spectral estimates or transport results, would materially affect the reviewer’s assessment.
-
What basis functions and parameter-selection strategies would the authors recommend for high-dimensional problems (where approximating eigenfunctions and their derivatives is known to be challenging)? What practical diagnostics can detect inaccurate eigenpairs or incorrect transported basin weights, even when the spectral coefficient diagnostic indicates convergence?
-
The unweighted Dirichlet-form estimator requires representative equilibrium sampling. What trajectory-design or coverage assumptions are required to recover the relative equilibrium weights of different basins? In particular, if the available trajectories remain confined to one basin, what information allows the method to determine the population of an unvisited basin? Can the proposed diagnostics detect this lack of information? How does the unweighted Dirichlet-form estimator accommodate trajectories initialized out of equilibrium?
-
The main spectral estimation appears to depend only on the empirical distribution of trajectory frames, with temporal information used separately for lag-consistency checks. Could the authors clarify whether the central task is learning dynamics from trajectories or estimating the generator of a reversible diffusion with prescribed diffusivity from stationary samples? What role does temporal information play beyond these checks?
4 comments
Part 2/2. (Q1 to Q4)
About diagnostics (Q1, Q2). The reviewer is right that the diagnostic of the submission can indicate convergence while the eigenpairs are wrong. It measures only the decay of the retained coefficients, and the paper now says so. The revision adds four checks, computed from the data and the output (lines 1592–1604).
- Transitions. The trajectory contains at least transitions between the wells where the estimated eigenpairs work in the scan, and at most where they fail with stationary data.
- Stationarity. The drift of the basin occupations between the two halves of the trajectory is at most on average for chains started in both wells, and and at and for chains started in one well.
- Generator and lag eigenvalues. Their relative difference for a retained mode, computed from the same pairs, vanishes for exact eigenpairs. Its median is at most where the estimated eigenpairs work and above where no run reaches the reference level.
- Output and data. The basin masses of the output differ from those of the stationary data by at most in the runs that reach the reference level and by to in the runs at .
Q2. We agree that a fixed grid of basis functions does not carry to high dimension. In three coupled dimensions a tensor grid with the per-axis resolution of the two-dimensional experiments reaches the reference level, and a coarser one does not (Appendix D.5). In higher dimension the eigenpairs should come from kernel estimators, with the full Gram matrix or a Nyström approximation, or from neural estimators, and the bounds of Section 4 transfer their errors without change. As for the choice of functions, bounded ones matter, since unbounded polynomials are unstable in the tails, and check 3 selects the retained modes from the data, as in the ten-dimensional example (Appendix D.2).
Q3. The data must sample the basins with their equilibrium weights and the transition layers between them. If the trajectories stay in one basin, no information determines the population of the other, for BKT or for any other method, and BKT then samples the law of the data. The scan with all chains started in the right well shows this (lines 1551–1557). The left-well fractions of the data are , and at , and , and BKT returns , and . Checks 1 and 2 detect this case, and for trajectories started out of equilibrium the reweighting of Wu et al. (2017) and Nüske et al. (2017) applies. Section 2 now states the data assumption (lines 155–160).
Q4. The reviewer's reading is correct. For a reversible diffusion with known diffusion matrix the generator is determined by , and the Dirichlet-form estimator of the paper uses the data only through the sampled states. The time order enters through checks 2 and 3, through estimators built on pairs , which BKT accepts without change, and through the reweighting of non-stationary data. The central task is to sample through the spectrum of the generator, estimated in weak form and without a density estimate. The abstract, the introduction, Section 2 and the conclusion have been reworded accordingly (lines 16, 58–65, 155–160 and 515).
For your convenience, we list the changes (magenta) made:
- Abstract, introduction, Section 2 and conclusion, the role of the dynamics and the data assumption (lines as above).
- Remark 4.3, wrong eigenvalues (lines 294–299).
- Section 5, the paragraph "High barriers" (lines 501–509).
- Appendix D.6 with Table 9 (lines 1536–1604).
- Appendix D.7, the limitations (lines 1606–1614).
We thank the reviewer again. The two tests led to Remark 4.3 and to the four checks, and we are glad to run any further test the reviewer finds useful.
The reviewer thanks the authors for their substantial revisions, additional experiments, and candid discussion of the observed failures. The reviewer will increase the score in recognition of these improvements and the clearer specification of the method’s limitations. The reviewer continues to appreciate the idea of using data from reversible processes to estimate the backward Kolmogorov generator and construct an explicit sampling flow.
The additional controls help distinguish spectral-estimation errors from numerical integration costs. In particular, the reviewer accepts that an extremely long physical relaxation time does not necessarily imply prohibitively expensive adaptive integration when an accurate velocity field is already available. The clarification that the principal Dirichlet-form estimator uses stationary sample locations and known diffusivity is also helpful.
The following points would further strengthen the manuscript. The reviewer is putting them here as a public record because everything will be publicly available regardless of the acceptance/rejection/withdrawn decision of the manuscript; this is to provide different aspects for future reviewers, practitioners, and even LLM's.
-
Relationship to McBride et al. (2026). The reviewer appreciates the added citation. A more detailed discussion would help distinguish the metastable relaxation timescale inherited from the diffusion, the computational cost of integrating an explicitly available spectral field, and the cost of acquiring data and estimating that field accurately. The new adaptive-integration results address the second but not the first and third.
-
Data acquisition and practical applicability. The revised coverage assumptions and barrier-height scan substantially clarify the requirements. However, the Gaussian-mixture tests show that even independent exact equilibrium samples, with correct basin coverage and weights, can leave the transition region insufficiently resolved and lead to unsuccessful transport. Could the authors discuss how practitioners should proceed in this situation, and more importantly, how does the practitioner know that they are in this situation?
-
Spatial eigenfunction approximation near the saddle. This remains the most important technical clarification. One has very few samples near the saddle, so constraining the eigenfunction there may be difficult. The failure with independent exact equilibrium samples in the Gaussian-mixture tests shows that equilibrium sampling alone does not ensure an accurate spectral estimate, particularly of the transition-layer profile and its derivatives. Accurate eigen analysis in the basins alone need not imply an accurate velocity field.
-
Interpretation of the diagnostics. The four additional checks are useful empirical warning signs, but their limitations should also be stated. The reviewer remains skeptical. Stable occupations can occur in a trajectory confined to one basin, and agreement between output and training occupations can reproduce biased training data. Generator–lag agreement on the same finite dataset likewise does not establish coverage of unvisited regions. Please distinguish detecting failures in the reported experiments from certifying reliable sampling more generally. The observation that a few hundred transitions suffice should also be qualified as specific to the tested configurations.
-
Basis selection beyond the demonstrated examples. The coupled three-dimensional experiment is helpful. The remaining question is how to select basis resolution, bandwidth, regularization, and retained rank when reference eigenpairs are unavailable, particularly to resolve transition-layer derivatives. Kernel and neural estimators are plausible alternatives, but their availability alone does not establish that they resolve this difficulty.
We thank the reviewer for deciding to increase the score and for stating the remaining points so precisely. We agree with all five, and the revised PDF states them in magenta.
1. We agree that the three quantities must be kept apart and that our adaptive-integration results address only the second. BKT follows the Fokker-Planck path and inherits its time to equilibrium, of order . With an explicit field this time is a parametrization of the path. In the variable a particle in a well moves along the gradient of the mean first-passage time to the other well, the measure of slowness of McBride et al., at a velocity of order one. The number of adaptive steps therefore grows only linearly with the barrier height. The exponential time returns in the data. The diffusion that they analyze as a sampler is the process that generates our trajectories, and in the scan these had to be several hundred times longer than . We therefore reach their conclusion. The field of BKT contains nonlocal information, the slow eigenpairs, and BKT moves the cost of metastability from the transport to the data without removing it (Remark 5.1, lines 510–521, and Appendix E).
2. This case can be recognized by counting the samples between the wells along a coordinate that separates them, or the transitions in a trajectory. In the scan the estimated eigenpairs work with about or more samples in and fail with about or fewer, and the mixtures have about four. Exact samples still determine the weights of the wells, but not or the profile of across the layer, which BKT needs, and no choice of the dictionary supplies them (lines 1637–1648). Samples in the layer must then be added. Appendix E reports a test with reweighted data from a simulation with a lowered barrier (lines 1749–1770). With these data is within of , and , and of ten runs reach the reference level at , and , compared with , and for unbiased trajectories.
3. We agree that this is the central point (lines 1623–1636). A function with the right constants in the wells is close to in whatever its profile in the layer, so accuracy in the basins says nothing about the field. The energy norm of our bounds does see the layer, where the energy of is concentrated, but the estimators replace it by an average over the samples, which sees the layer only through the samples that fall into it. Theorem 4.5 requires more, since the paths of the particles through the layer must stay in the validity region, whose conditions are pointwise. The basins matter as well, because the particles move with , a ratio of two quantities of order there. In the biased test an eigenvalue that is to too large alone lowers the left-well mass from to , and at the estimated eigenfunctions limit the result although the layer contains about samples.
4. It's correct and the paper now calls the checks warning signs that do not certify the output (lines 1650–1654). For the chains started in the right well at the occupations in Table 9 are stable, with a drift of , and the output reproduces the weights of such data, with for at . Agreement of the generator and lag eigenvalues says nothing about regions without data. The checks also miss failures within the scan, since at they do not separate the four realizations that miss the reference level from the six that reach it. The few hundred transitions are specific to the tested configurations, as the paper now says.
5. We acknowledge that the paper gives no general rule and it now says so (lines 1656–1666). Ranking dictionaries by their estimated eigenvalues is not sufficient. In our three-dimensional example the slow eigenvalues of the coarse dictionary are within of the reference values, and yet the output keeps of the mass in the initial well where the finer dictionary gives . Refining the dictionary until the output no longer changes shows this without a reference, but it sees a transition layer only through its samples. The same holds for kernel and neural estimators, which avoid the exponential growth of a tensor dictionary with the dimension but are fitted to the same samples (line 498).
Changes made (in magenta).
- Section 2, the data must also sample the transition regions (lines 155–160).
- Section 5, the sentence on kernel and neural estimators (line 498) and Remark 5.1 (lines 510–521).
- Appendix D.7, rewritten (lines 1612–1666).
- Appendix E, new, with Table 10 (lines 1668–1777).
We thank the reviewer again. These comments have made the limits of the method clearer and new paper is updated.
Part 1/2. (Weakness, Q1)
We thank the reviewer for the most demanding review we received. Running our code on two tests is the necessary validation the paper needed. In the revised PDF, the changes we made for this review are in magenta and the changes we made on our own are in blue. The line numbers below are those in the margin of the PDF.
First we want to clarify our position in brief. The review is right on three points, and the paper now reflects them. First, the submission named the limitation at high barriers without quantifying it. Second, the diagnostic χ^2 does not detect wrong eigenpairs. Third, the Dirichlet-form estimator uses the data through the stationary samples, so the submission overstated the role of the dynamics (Q4). On one point we reach a different conclusion. The two tests fail in the estimation of λ1 and φ1, which no method can obtain from data without samples in the transition layer, whereas the transport itself works across these time scales at a small cost.
Regarding to the two tests, for s2=0.012 the barriers are 33.1 and 34.2 in units of the temperature, and the two-state formula gives λ1=7.5⋅10−13 and 1.3⋅10−12. About four of 2⋅105 exact samples fall in ∣x∣<0.45, and none near the saddle. We reproduced both tests (lines 1559–1565 and 1586–1590).
The transport therefore works at 33 units, at a cost of about a hundred steps per particle, and the failure comes from the estimate of the slow eigenpair.
Now we want to explain why a longer integration cannot help. By the new Remark 4.3 (lines 294–299), wrong eigenvalues do not simply rescale time. If the eigenvalues are too large by a factor κ, the particles follow the field vκt and move κ times slower than the exact flow, so the field has decayed before the mass has crossed. In the reviewer's discovery test the estimated gap was about 6.8⋅106 times the reference value. The estimated field was therefore negligible after about a millionth of the reference time scale, and integrating up to ten mean first-passage times could not move any mass.
We also want to clarify the limit is in the data. The estimators are functions of the sampled states. If no sample falls in the transition layer, the barrier height is not determined by the data, for our estimator and for any other (lines 1538–1539). This is the limitation the review describes, and no change of the transport can remove it. The scan below quantifies it, which the submission had not done.
Q1. The regime in which estimation and transport work. For V=a(x2−1)2, a∈{1,2,3,4,6,8,10}, we used the data protocol of the paper (2⋅105 pairs from 500 chains, lag 0.1) over ten realizations (Table 9, lines 1541–1557).
The practical range is therefore set by the number of observed transitions, a few hundred here, rather than by the relaxation time. This agrees with the reviewer's analysis of the data requirement and with McBride et al. (2026), which Section 5 now cites (lines 501–509).
Regarding to the cost across time scales, the concern that the particles must be integrated at the cost of the slow time scale does not apply to BKT. The field is explicit in t and the equations of the particles are decoupled, so each particle is integrated with its own adaptive step in physical time (lines 1547–1549). A particle takes small steps while it crosses a barrier and large steps otherwise. This means 20 to 48 accepted steps on average in the scan and about 100 for the exact pair at 33 units, where the relaxation time is 109 times longer than at a=10.