- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper proposes a formulation of diffusion as a control problem that has energy loss, the mismatch in the marginal distribution at every time loss, and the mismatch of the joint finitely many observation time path loss. This fits into the framework of MecKean-Vlasov forward-backward-SDE. The paper proposes a way to use that for training a neural network in order to fit a drift.
Critical strengths
It is quite interesting to see a new formulation of diffusion as a control problem.
Critical weaknesses
It is not clear whether the algorithm 1 will converge or not. My understanding is that the paper just shows that a stationary point (or approximate due to discretization) exists due to Theorem 1, but it is not clear whether such stationary point can be obtained. Also, algorithm 1 requires the compression of the past history with a fixed and exogenously given function. This seems to limit the expressivity of the numerical conditional expectation computation. I also fail to see the novelty of the algorithm given that it essentially is the same as attempting to solve the system of PDE which is known to the control community and fit the model with neural network. It could be that I am wrong on this and that the novelty of applying the known technique from control is sufficiently good.
General diffusion paper normally addresses what the algorithm would be if there is unlimited amount of data and expressivity of neural network. In this paper, it is unclear what the limit will be. Currently, the use of soft path-law constraint seems like an excuse so that we can use the forward-backward SDE instead of the paper claim about that soft constraint seems to genuinely good for generalization and prevent overfitting.
Questions for authors
Can the author explain more about the experiment in 4.1? In the current framework, the energy part of the loss cannot make the coefficient to be location or time specific, so how do we add the partitions into the calculation?
How do we normally get an observation of a continuous time process? Is this done by discretization? If so, would it be better to use ushc discretized process and the joint path instead of the integral of marginal loss?
5 comments
Thank you for your rebuttal. I may mistakenly think that the FBSDE can be changed into PDEs, but it seems like it cannot, and the solver in your paper just do numerical iteration (where in each iteration we more or less do numerical mean for Yt), right?
I am not so sure how solving FBSDE in a numerical and a very starightforward manner can be counted as a good contribution. Are you thinking more like some empirical proof that the method can work in this area?
Thank you for your remark. In fact, there is a dual representation between FBSDE and PDEs in our path-dependent formulation. Indeed, solving the optimal control problem would lead to a system of coupled PDEs where each PDE is written over each the subintervals and are linked through the jump terms in our paper. In this paper, we wanted to focus more on the FBSDE representation which we believe has a straightforward interpretation and relies on more probabilistic tools. Concerning the numerical solver, we are indeed performing an iterative approach. However, we want to point out that our algorithm is first sample-based in the sense that the law-functionals (law-gradient terms) need to be estimated from observed samples and trajectories generated by the current control and recomputed as the generated laws change. Moreover, it needs to tackle the jump terms, which is also a novelty of our path-dependent approach. As we mention, the solver has to handle this jumps by computing the conditional expectation with respect to the available trajectory history.
By the way, what do you mean by numerical mean of ?
Rebuttal Answer
We thank the reviewer for his comment and address your comments below.
General comment. The optimal control is not obtained from a PDE system but from the probabilistic FBSDE representation: αt⋆ is the pointwise minimiser of the Hamiltonian a↦H(t,X,PX,Xt,PXt,Yt,Zt,a), i.e. αt⋆=a^(t,X,PX,Xt,PXt,Yt,Zt). In our setting αt⋆=−Yt, but the FBSDE must still be solved numerically, which is one of our contributions.
Convergence. A general convergence proof is beyond the scope of the paper, but convergence holds for benchmark problems (see our answer to Q3 of Reviewer Jv5k). Dimensionality reduction for conditional expectations is used only in the high-dimensional AMASS experiment, not in the detour one. Our method approximates the FBSDE directly, with neural networks for the backward process; this differs from direct optimisation of the control ("Direct SDE" in the paper).
Motivation for soft constraints. The penalty λ>0 trades off control energy against fidelity to the target, and the relaxation leads to a mean-field control problem whose analysis requires extending the stochastic maximum principle to our path-dependent setting with discrete observation times, a main mathematical contribution. The hard constraint is recovered as λ→∞. With Jλ(α):=E[21∫0T∣αt∣2dt]+λD(P(Xs1α,…,XsKα)∣ρ), a minimiser αλ and any feasible αˉ (with D=0) give
λD(P(Xs1αλ,…,XsKαλ)∣ρ)≤Jλ(αλ)≤Jλ(αˉ)=:C<∞,
so D≤C/λ→0. The FBSDE formulation is also interpretable: the control is characterised by the backward process, directly linked to the gradients of the distributional discrepancies. (Q2 of Jv5k)
New experiment: soft vs hard constraints with little data. We compared our marginal-only solver with a neural multi-marginal Schrödinger bridge, using 24 and 96 training observations per date, independent test observations, and the same shared network and diffusion coefficient. Schrödinger bridges impose the marginals as equality constraints (Léonard, 2014; multi-marginal: Di Marino & Gerolin, 2020); our comparator adapts the empirical construction of Pooladian & Niles-Weed (2025) to multiple dates. Our penalty weights are fixed across dataset sizes.
Change = relative train-to-test change of MMD2 (one seed). The bridge fits more tightly (lower absolute test MMD2), but its discrepancy nearly doubles on unseen data with 24 observations (+24% with 96), whereas ours is stable at both sizes. This supports the regularising role of finite penalties: our fit transfers to unseen data with essentially no deterioration, even with little data.
Q1. We solve a single control problem over the whole horizon, so no partition is needed. With observation grid Πobs={s1,…,sK}⊆Πsim={t0,…,tN}, the control αt=Yt is càdlàg: at sℓ=tm, αtm=αtm−+ΔYsℓ, where the jump is induced by the discrepancy gradient (Eq. (2.8)). These jumps are thus already in the scheme, and ∫0T∣αt∣2dt≈∑m=0N−1∣αtm∣2Δtm on the simulation grid.
Q2. Observation times are fixed in advance on Πobs⊆Πsim, while the process evolves continuously; continuous time is more tractable for the mean-field FBSDE, though a discrete-time version is possible. Our constraint involves the joint law P(Xs1,…,XsK), not the full path law PX⋅∧t, so the marginal flow (PXt)t≥0 carries extra information between observations. A full-path formulation is possible but numerically harder; ours stays realistic since data are observed at discrete times. Since Πobs can be strictly smaller than Πsim, integrals are approximated on the whole simulation grid.