- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies MCMC distillation for training an implicit neural sampler from an unnormalized target density. Training alternates between short MCMC refinements initialized from the current generator and fitting the resulting teacher distribution using sample-based discrepancies. The paper develops a conditional weak-convergence framework that separates reference mixing, fitting error, and transition bias, with specific results for Langevin teachers. Experiments evaluate MMD and sliced-Wasserstein fitting on four two-dimensional targets, a logistic-regression posterior, and a conditioned-diffusion posterior.
Critical strengths
-
The approach avoids evaluating the generator density and produces independent samples in a single forward pass after training.
-
The theoretical framework explicitly distinguishes fitting error from teacher transition bias. The paper also acknowledges the mismatch between its theoretical and practical step-size schedules.
Critical weaknesses
-
Limited algorithmic novelty and no competing neural-sampler baselines. The refinement-and-fitting procedure follows established amortized MCMC [1], as the paper acknowledges. Although the convergence analysis is a distinct contribution, the experiments do not establish the practical value of the proposed fitting objectives relative to existing learned samplers. ULA is the only external sampling baseline; the MMD and sliced-Wasserstein variants are both instances of the proposed method. Relevant comparisons include the amortized-MCMC approach and kernel semi-implicit variational inference [2], both already cited by the submission. Diffusion-based methods for unnormalized targets, such as Denoising Diffusion Samplers [3], also provide relevant context.
-
Limited experimental evidence for efficiency and scalability. The experiments cover four two-dimensional targets and two Bayesian posteriors, but provide no training-time, memory, sampling-throughput, or amortization measurements. Matching teacher transition counts does not account for generator optimization and discrepancy evaluation. Pairwise MMD scales quadratically with batch size, whereas sliced Wasserstein has projection and sorting costs; their practical trade-offs should be measured. Sinkhorn fitting is analyzed but not evaluated experimentally. Moreover, the conditioned-diffusion ELM diagnostic measures coordinatewise densities and explicitly omits temporal dependence (Appendix B.5), limiting the evidence for accurate joint sampling.
-
Recovery of global mode weights is not demonstrated. Correct mode probabilities are essential for multimodal sampling, beyond locating modes and matching their local geometry [4]. If short teacher chains rarely move between modes, their output can retain incorrect mode proportions, which the generator is then trained to reproduce. Repeated refinement and the annealing used in some experiments may help, but the paper does not demonstrate that they recover correct weights within the training budget. The eight-Gaussian example uses equal weights and reports no explicit mode-weight errors. An unequal-weight mixture with controlled separation and deliberately imbalanced initialization would directly test this concern.
-
The conditional guarantees do not establish the accuracy of practical training. Theorem 4.6 requires mixing and stability assumptions, vanishing ULA step sizes, and population fitting errors satisfying . The paper does not establish that its finite-batch optimization achieves this error condition, and its practical step-size schedules differ from those required by the theory. The result therefore does not resolve the finite-budget mixing and mode-weight concerns above.
[1] Yingzhen Li, Richard E. Turner, and Qiang Liu. Approximate Inference with Amortised MCMC. arXiv:1702.08343, 2017. Paper.
[2] Ziheng Cheng, Longlin Yu, Tianyu Xie, Shiyue Zhang, and Cheng Zhang. Kernel Semi-Implicit Variational Inference. ICML, 2024. Paper.
[3] Francisco Vargas, Will Grathwohl, and Arnaud Doucet. Denoising Diffusion Samplers. ICLR, 2023. Paper.
[4] Louis Grenioux, Maxence Noble, and Marylou Gabrié. Improving the Evaluation of Samplers on Multi-Modal Targets. ICLR, 2025. Paper.
Questions for authors
-
What benefits do the proposed fitting objectives provide over closely related learned samplers when training cost and sampling accuracy are both considered?
-
Can the method recover unequal mode weights from an imbalanced initialization, and how does this depend on mode separation and the teacher-refinement budget?
-
What evidence connects the population fitting-error condition in Theorem 4.6 to the implemented finite-batch optimization and step-size schedules?