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 .