Learning a neural sampler can reduce the cost of repeated sampling from an un-normalized distribution, but obtaining good training data remains difficult. We develop a corrected self-training scheme across a sequence of tempered targets, making use of importance sampling and Markov chain Monte Carlo to correct the samples and replay buffers to store them. We introduce Sequential Score Sampler (SSS) as a particular case. In SSS, the proposal is a score-based diffusion trained by regression on energy gradients; and the samples are corrected by importance weights on the path space. After training, samples can be collected directly from the model, from its importance-corrected proposals, or from the final-temperature buffer. The method amortizes repeated sampling by encoding the global structure of the target in the model. SSS achieves competitive sampling accuracy across the benchmarks and, on several targets, uses shorter runtimes with fewer energy evaluations than competing samplers.
Figures & tables
Figure 1: Corrected self-training across temperatures.
Figure 2: Ablation of the path-space correction on DW-4, final generated samples (orange) and ground truth (blue). Each panel shows the three sample sets of SSS (from left to right): raw samples, importance-corrected samples, and the replay buffer. The top row shows the distribution of inter-particle distances rij and the bottom row shows the energy distribution.
Figure 3: Ablation of the HMC rejuvenation on DW-4, evaluated at β=1 midway through training (orange) and ground truth (blue). Each panel shows the three sample sets of SSS (from left to right): raw samples, importance-corrected samples, and the replay buffer. The top row shows the distribution of inter-particle distances rij and the bottom row the energy distribution.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Target
TA-BG
PITA
SSS
AS
GMM16 ( d=16 )
40
105
6
2
GMM50 ( d=50 )
55
190
43
6
DW-4 ( d=8 )
80
530
15
13
LJ-13 ( d=39 )
—
—
552
538
Alanine Dipeptide
—
—
366
351
Appendix
Table 3: Wall-clock time (in minutes) for the separately timed runs. All runs were executed on a single NVIDIA RTX 4500 Ada Generation GPU. The LJ-13 and Alanine Dipeptide results of TA-BG and PITA are taken from Akhound-Sadegh et al. (2025) , so no timing is reported.
Particles
HMC moves per temperature
Runs retaining the far mode
1,000
1,000
3%
3,000
330
13%
5,000
195
25%
10,000
97
36%
20,000
47
50%
50,000
17
71%
Appendix
Table 10: Far-mode retention in the eccentric Gaussian mixture at a fixed SMC energy budget. Each row summarizes 100 runs.
Figure 4: Marginal densities of x1 at β=1 for the selected seed, starting from SMC populations of 1,000 (left) and 80,000 (right) particles. Each panel compares the initial SMC population, corrected SSS samples, and exact samples. Insets report the corresponding far-mode shares, with exact target mass 0.50 .
Monte Carlo sampling algorithms aim to produce samples from a target distribution with a given unnormalised probability density function. The high cost of running Monte Carlo algorithms, with many simulation steps or particles needed to obtain a good empirical approximation to the target, can be reduced by introducing learnable components into the sampler -- a form of amortisation. Once these components are trained, amortised samplers can produce high-quality samples with less computation at sampling time than training-free algorithms would require. We propose an amortised sampler built upon the framework of adaptive importance sampling -- a hierarchical importance sampling procedure where the proposal is iteratively adapted. Our amortised adaptive importance sampling algorithm fits a lightweight neural network that adapts the proposal using information obtained over the course of sampling. By training our sampler over many different targets taken from the same family of distributions, we obtain a sampler that can adapt to a specific target at sampling time without a priori access to the target's parameters. We show that our procedure can efficiently sample from targets within the family the sampler was trained on, giving improvements over target-specific amortised samplers and training-free adaptive importance sampling algorithms. We also explore the potential for generalisation, where the trained sampler is used to sample from targets outwith its training family.
Arran Carter, Víctor Elvira, Esmeralda S. Whitammer
Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \teacher) to guide the training of the primary amortized sampler (the \student). The \teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.
We develop diffusion-based samplers for target distributions known up to a normalising constant. To this end, we rely on the well-known diffusion path that smoothly interpolates between a simple base distribution and the target, popularised by diffusion models. We tackle the score estimation problem by developing an efficient sequential Monte Carlo sampler that evolves auxiliary variables from conditional distributions along the path, providing principled score and density estimates for time-varying distributions. To control the variance of score estimates, we further propose practical control variate schedules that incur minimal overhead. We adapt this general framework to paths induced by the Ornstein-Uhlenbeck (OU) time-reversal process, stochastic interpolants, and diffusion annealed Langevin dynamics, outlining their trade-offs. Finally, we provide theoretical guarantees and empirically demonstrate the effectiveness of our method on several synthetic and real-world datasets. Our code is available at: https://github.com/akyildiz-group/dpsmc.
James Matthew Young, Paula Cordero-Encinar, Sebastian Reich +2
Department of Mathematics, Imperial College London, UK · Institut für Mathematik, Universität Potsdam, Germany