- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper establishes the equivalence between the Doob’s Lagrangian framework and Freidlin–Wentzell (FW) large-deviation theory. Specifically, the paper proves that minimizing the Doob action asymptotically equals computing a quasipotential of Arrhenius–Kramers transition rates, motivating the initialization from a stationary committor function. The evaluation is on alanine dipeptide and Chignolin.
Critical strengths
- The theory is solid and explains why fixing the transit time T leads to suboptimal minimization of the FW action, motivating the joint optimization of (v,T).
- The connection to the FW action functional seems novel and is an interesting theoretical contribution that could lead to follow-up ideas and methods.
Critical weaknesses
- It is questionable whether the training scheme will scale to larger systems, since it requires initialization with a stationary committor function (which may not be well defined for many systems), pretraining a generative model to match the stationary committor function, then minimizing T. Evaluation on larger systems beyond ALD and Chignolin are needed.
- It is hard to tell whether the method will generalize, since the guarantees assume vanishing noise and a single transition channel. The current molecular experiments run at zero noise and the toy results suggest accuracy degrades at finite noise.
- All molecular comparisons are limited to DL variants. Classical methods and learned path samplers ([1], [2], [3]) seem to be missing.
[1] Holdijk, L., et al. (2023). Stochastic optimal control for collective variable free sampling of molecular transition paths.
[2] Seong, K., et al. (2025). Transition path sampling with improved off-policy training of diffusion path samplers.
[3] Raja, S., et al. (2025). Action-minimization meets generative modeling: Efficient transition path sampling with the Onsager-Machlup functional.
Questions for authors
- How does the method scale to larger proteins? How does the cost of committor estimation compare with the cost of DL training?
- How much does the DL optimization improve over the committor-generated path it is initialized from?
- How does the method perform with multiple competing transition channels, or at finite noise?
9 comments
Rebuttal to Reviewer FfUU (Weakness 2)
It is hard to tell whether the method will generalize, since the guarantees assume vanishing noise and a single transition channel. The current molecular experiments run at zero noise and the toy results suggest accuracy degrades at finite noise.
The vanishing-noise limit in our theory is the standard asymptotic regime of large-deviation theory. In this regime rare-event rates take the Arrhenius-Kramers form , and reactive trajectories concentrate around the minimizers of the Freidlin-Wentzell action (Freidlin and Wentzell, 1984; Hänggi et al., 1990; Bouchet and Reygner, 2016). This is the setting in which the objective optimized by DL acquires a physical interpretation. Theorem 3.1 identifies the minimum of the Doob action over with the quasipotential that sets the rate exponent, and this identification motivates both the optimization of and the committor initialization. As in Kramers' theory, small noise means small relative to the barrier, so the limit describes the regime in which transitions are rare and path sampling is needed. The theory is stated in the limit , while the method itself runs at finite .
All molecular experiments are run at finite temperature, 300 K for alanine dipeptide and Trp-cage and 500 K for chignolin, and the corresponding noise amplitude enters the Doob action that is optimized. The quantity we set to its minimum is the width of the Gaussian marginal. The optimization therefore returns the mean path, which is the most probable transition path at the simulation temperature and the object computed by minimum-action methods such as MAM and gMAM. We made this choice because in Cartesian coordinates small perturbations of the bond lengths produce large changes in energy, so the stochastic estimate of the action is dominated by bond vibrations and training becomes unstable. In order to address this comment we added experiments with non-zero sampling variance on alanine dipeptide, reported in Appendix C.1. With the path parameterized in internal coordinates, that is the full set of bond lengths, angles and dihedrals from which the molecule is reconstructed, the model trains stably at finite width and returns an ensemble of reactive paths, all 64 of which reach (Figure 6).
The degradation in the toy results of Appendix B (Table 1) occurs when the noise becomes comparable to the barrier. On the double well, where , the ratio equals 1.00 for every , that is . It grows to 1.48 and 3.64 at and , where and transitions are no longer rare. In that regime the quasipotential, a small-noise quantity, no longer describes the transition, and the Doob action at finite noise departs from it, consistently with Theorem 3.1 being a statement about the limit . The molecular systems lie well inside the first regime. For alanine dipeptide at 300 K the barrier of 37.9 kJ/mol gives a ratio of approximately 15, where the double-well ratio is 1.00.
The single-channel condition of Assumption 3.1 is a hypothesis of the convergence guarantee of Theorem 3.2, and the algorithm runs without it. With competing channels a single Gaussian follows the channel in which it is initialized. The Gaussian-mixture parameterization of Du et al. (2024), in which each component is initialized from a distinct committor-based path and carries its own transit time, recovers all of them. We report this extension in the new Appendix D (Figure 8). On a two-dimensional two-channel potential the learned channel weights match a grid reference to within 0.03, and on alanine dipeptide four components retain four distinct channels (see our reply to Question 3).
Rebuttal to Reviewer FfUU (Weakness 3)
All molecular comparisons are limited to DL variants. Classical methods and learned path samplers ([1], [2], [3]) seem to be missing.
We added a comparison on alanine dipeptide with the learned samplers suggested by the reviewer, reported in Appendix C.1 (Table 3). We ran TPS-DPS (Seong et al., 2025) and Onsager-Machlup action minimization (OMA, Raja et al., 2025), together with the original Doob's Lagrangian (Du et al., 2024). We could not obtain a working run of PIPS (Holdijk et al., 2023), which failed to produce reactive paths with two different seeds. Each method was run with the alanine dipeptide settings of its paper and repository on a common system, the amber14 force field in vacuum with our endpoint structures. Following Park et al. (2025), we evaluated 64 paths per method through the fraction of paths reaching , the RMSD of the final structure to , the barrier height along successful paths, and the computation time.
| Method | Hits | RMSD (Å) | Barrier (kJ/mol) | Train (s) | Sampling (s) |
|---|---|---|---|---|---|
| DL + committor + flexible (ours) | 64/64 | 0.00 | 31,140 | 1.9 | |
| DL, linear + fixed | 64/64 | 0.00 | 7,059 | 1.9 | |
| TPS-DPS (seed 2) | 0/64 | 0.79 | n/a | 39,226 | 202 |
| TPS-DPS (seed 3) | 60/64 | 0.22 | 36,767 | 198 | |
| OMA | 61/64 | 0.01 | 34,206 | 337,395 |
Our method has the lowest barrier, every path reaches by construction, and the total training time, which includes the committor stage, is below that of TPS-DPS and OMA, while sampling is two to five orders of magnitude faster. It also corrects the failure of the original DL, whose paths reach only over a barrier of 933 kJ/mol. The barriers are not strictly comparable across methods, since ours generates configurations directly, TPS-DPS samples biased trajectories that carry thermal noise, and OMA minimizes the energy of every generated frame with L-BFGS. Even so, our paths have energies comparable to those of the minimized OMA structures, whose mean is kJ/mol once five paths with barriers above 200 kJ/mol are excluded. The first TPS-DPS run produced no reactive path and a second seed was needed, and the final relaxation of OMA diverged for 3 of the 64 paths.
Rebuttal to Reviewer FfUU (Weakness 1)
We thank the reviewer for their comments. We respond point by point below. In the revised manuscript all modifications are highlighted in blue.
Critical Weaknesses
The molecular experiments of the submission reproduce the setting of Du et al. (2024), our primary baseline, in which chignolin is the largest system considered. We extend the evaluation to a larger protein below, after some remarks on the requirements of the pipeline.
The stationary committor exists and is unique for any pair of disjoint states A and B. It is the solution of the backward Kolmogorov equation Lq~=0 with q~=0 on ∂A and q~=1 on ∂B, and existence and uniqueness follow from the maximum principle for a nondegenerate generator (E and Vanden-Eijnden, 2006), independently of the complexity of the landscape. Theorem 3.2 is stated for this function. In practice the method uses the committor through the algorithm of Mitchell and Rotskoff (2024), which refines an estimate of the committor while sampling the transition region, and from which we take one reactive trajectory from A to B. What the initialization needs from the estimate is therefore a trajectory in the dominant reactive channel, and the optimization of the Doob action then refines the path within that channel. The two steps that follow add almost no cost. Fitting the model to the reactive trajectory is a regression on a few tens of frames, and optimizing T adds no gradient evaluations, since the path is a continuous function of t∈[0,T] sampled with a fixed batch size.
We extended our evaluation to the folding of Trp-cage (20 residues, 284 atoms, about twice the size of chignolin), with the folded and unfolded structures of Seong et al. (2025), reported in the new Section 4.4 and Figure 4. The initialization did not become harder with size. The committor algorithm produced a reactive trajectory after 83 iterations, against 729 for chignolin, at a cost of 9.3×106 force evaluations and 64 minutes, the fit took 47 seconds, and the DL optimization took 8.6×107 evaluations and 21.8 hours. The resulting path is free of steric overlaps and has a single interior maximum 445.9 kJ/mol above its minimum, on the same scale as the 395.5 kJ/mol found for chignolin. The original DL with linear initialization and fixed T, given the same budget, remains trapped in an unphysical path with overlapping atoms and a maximum of 7.8×1016 kJ/mol. The cost analysis and further details are given in our reply to Question 1.