- Rating
- 4
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper presents D3Opt, a framework for chance-constrained programming that disentangles constraint modeling from objective optimization. In the first stage, feasible decision data are generated using constraint information only (no objective evaluation), and a risk-conditioned diffusion model is trained and frozen. In the second stage, a post-specified objective — possibly non-convex, non-smooth, and accessible only through function values — is introduced at inference time via an annealed, particle-based Feynman–Kac correction along the frozen reverse diffusion, reweighting and resampling particles by objective values to concentrate mass on low-objective regions. Theoretically, the authors prove that the correction preserves the support of the frozen prior (feasibility preservation) and derive an optimization-error bound decomposing into coverage, finite-particle, and finite-temperature terms. Experiments cover linear Gaussian CCPs, objective transfer with the same frozen checkpoint (smooth convex and non-convex non-smooth objectives), chance-constrained economic dispatch with valve-point effects, multi-risk adaptation, and robust waveform design
Critical strengths
- Data generation, diffusion training, and frozen inference never touch the objective; the FK potentials depend only on objective values at denoised predictions and telescope to the desired terminal Boltzmann tilt. The same checkpoint transfers to ASQ (smooth convex) and MW4 (non-convex non-smooth) without retraining, directly validating the decoupling claim. 2.Comparisons span convex exact references (SOC-CVX), SAA variants, GGDOpt, DiffOPT, and classical methods (DE, PWL-MILP, sphere bounding, Bernstein); tasks include objective transfer, multi-risk levels, ablations, a non-smooth practical application, and a non-convex objective. The frozen checkpoint is reused across four risk levels with all returned solutions satisfying the analytic chance constraint.
Critical weaknesses
1.Coverage error is the only term in the decomposition that does not vanish with particles or temperature, yet the paper provides no way to measure or bound it. The choice of proposal distribution strongly affects coverage (the gap between 0.8549 without FKC and ~0.098 for the ASQ optimum shows the prior is heavily biased toward suboptimal regions), and this most sensitive component receives no sensitivity analysis or diagnostic. 2.Feynman–Kac correction and SMC are mature tools, and Skreta et al. 2025 already applied them to diffusion inference steering. The increment here is the combination of an objective-free prior with telescoping potentials. An ablation showing why evaluating potentials at denoised predictions is superior to evaluating them at particle states would substantiate the design choice.
Questions for authors
How can the coverage gap be estimated? For example, can the paper report the prior's probability mass near the global optimum sublevel set for each task, or at least ablate the proposal distribution (uniform vs. others) to demonstrate sensitivity?
2 comments
For W2: Objective Evaluation at Denoised Predictions
Thank you very much for this helpful suggestion. To examine this design choice, we compare objective evaluation at denoised predictions, , with direct evaluation at noisy particle states, $f(X_k) $. Within each task, we retain the original checkpoint, risk level, particle count, reverse-diffusion steps, inverse-temperature schedule, and ESS resampling rule. Both variants use the same telescoping FK construction, terminal decision definition, and feasibility correction and selection protocol. Only the intermediate objective-evaluation input is changed. Each variant is evaluated over 100 inference runs.
Objective-evaluation ablation under the original experimental protocol. Bold indicates the lower mean and standard deviation within each task.
| Task | Objective evaluation | Repeat | FvalMean ↓ | FvalStd ↓ |
|---|---|---|---|---|
| Linear Gaussian | Noisy-state | 100 | −0.6492 | 0.0031 |
| Linear Gaussian | Denoised (ours) | 100 | −0.6519 | 0.0015 |
| ASQ | Noisy-state | 100 | 0.1231 | 0.0034 |
| ASQ | Denoised (ours) | 100 | 0.1035 | 0.0018 |
| MW4 | Noisy-state | 100 | 0.2178 | 0.0102 |
| MW4 | Denoised (ours) | 100 | 0.1834 | 0.0018 |
| CCED | Noisy-state | 100 | 106244.87 | 153.281 |
| CCED | Denoised (ours) | 100 | 104823.58 | 102.065 |
The table shows that denoised evaluation yields lower mean objectives and smaller standard deviations on all four tasks. Relative to noisy-state evaluation, the mean objective decreases by 0.0027 on Gaussian and by approximately 15.9%, 15.8%, and 1.34% on ASQ, MW4, and CCED, respectively. These results support using denoised predictions for objective evaluation in finite-particle optimization under the tested settings.
We hope our responses address your concerns, and we would be very grateful if you could raise your score, as this would mean a great deal to us.
For W1: Coverage error and sensitivity to the training-data proposal.
Thank you for your comments on the coverage error. We provide a quantitative diagnostic using unguided diffusion sampling. For the linear Gaussian CCP with n=8 and ρ=0.1, we draw 10,000 raw samples and compute the minimum objective among those. Let IN,ρ denote their indices. Under the almost-sure feasibility assumption in Proposition 2, we have
0≤∣fρ⋆∣Δθ,ρ≤∣fρ⋆∣mini∈IN,ρf(Xi)−fρ⋆almost surely.
Thus, this statistic gives a finite-sample upper bound on the relative coverage error; the true gap can be smaller. For CCED-VPE-10, we additionally report the best returned cost from the w/o FKC evaluations and its gap to the numerical DE reference.
Unguided-sampling diagnostics under different training-data proposals at ρ=0.1. For Linear Gaussian, fmin is the minimum feasible objective among 10,000 raw samples, and fref is the exact SOC optimum. For CCED-VPE-10, fmin is the best returned cost from the w/o FKC evaluations, and fref is the DE reference with exact projection. Relative gaps are 100(fmin−fref)/∣fref∣.
The tested proposal replacements give similar observed gaps within each task: Student-t5 gives a slightly tighter Gaussian bound, while the original uniform proposal gives a slightly lower CCED reference gap. Appendix D.2 (Table 9) also reports a controlled proposal-sensitivity experiment. For each proposal, we regenerate the training data and retrain the prior, keeping the retained sample count, network, training budget, and FKC settings fixed. The final mean objectives are −0.6519 vs. −0.6521 on Linear Gaussian and 104823.577 vs. 104904.758 on CCED-VPE-10. These results show similar final objective values under the tested proposal replacements. The appendix also includes objective-value histograms of the training data and unguided outputs as a descriptive diagnostic.
Regarding ASQ, it's an objective-transfer experiment. The value 0.8549 reflects the mean quality of unguided returned solutions and does not directly measure the coverage gap. The results shows that, with the same frozen checkpoint, FKC improves the ASQ mean objective from 0.8549 to 0.1035 and the best objective from 0.3209 to 0.0999, compared with the optimum of 0.0979. This ablation demonstrates the role of FKC in directing sampling toward low-objective regions while keeping the feasibility model fixed.