Sampling ideas

Diffusion step schedules, solvers, guidance and stopping rules that cut function evaluations or improve sample quality.

2 ideas found

Category: Sampling ML: Graph nn Math: Stochastic processes Clear all

✗ Failed on benchmark 2026

Second-order fusion prior for point-set diffusion

Add the paper's local Sine_beta fusion law as an analytic score prior for diffusion models that generate unordered point configurations. The model is trained to match both the usual diffusion score and an explicit short-range repulsion score, including the second-order correction that describes finite-scale fused configurations.

Useful6/10

Difficulty5/10

Novelty6/10

Sampling Accuracy Stability Sample efficiency

Paper: Second-order Fusion Asymptotics for Sine\b{eta} Correlation Functions arXiv:2608.23742

Unverified 2026

Spectrum-preserving conditional binary graph sampler

Build a graph-structured binary latent layer whose local heat-bath probabilities are predicted by a neural network, while particle-exchange and refresh rates remain fixed. The learned probabilities change the stationary distribution and encode input-dependent conditioning, but the spectral invariance result predicts that they do not change the Markov-chain eigenvalues or relaxation modes. This provides a conditional sampler with a fixed, calibratable mixing budget instead of requiring a new…

Useful5/10

Difficulty5/10

Novelty8/10

Sampling Stability Sample efficiency Graph nn

Paper: Mixing times and spectra of non-equilibrium symmetric exclusion processes on general graphs arXiv:2607.22991