arXiv Machine Learning
Iterative Exact Discrete Guidance for Energy-Based Sampling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 28
Sampling Decisions: Exact Path-Space Correction, Prior Cancellation and Local-Boltzmann Guidance
arXiv:2503. 14549v3 Announce Type: replace-cross Abstract: How can a cheap but biased sequential, finite-horizon sampler over a discrete space be corrected so that its terminal output follows a prescribed Gibbs distribution?
arXiv Machine Learning
Aug 4
Sampling Decisions: Exact Path-Space Control for Physics-Informed Generative Sampling
arXiv:2503. 14549v4 Announce Type: replace Abstract: Scientific generative models must turn tractable local decisions into globally correlated samples that respect physical constraints.
arXiv Machine Learning
Jul 20
Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling
arXiv:2607. 15682v1 Announce Type: new Abstract: Sampling from an unnormalized Boltzmann density requires proposals that move probability mass globally while retaining enough path-probability information for statistical correction.
arXiv Machine Learning
Jul 9
Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
arXiv:2607. 07665v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules.
arXiv Machine Learning
Jul 23
Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes
arXiv:2601. 21026v2 Announce Type: replace-cross Abstract: Sampling configurations at thermodynamic equilibrium is a central challenge in statistical physics.
arXiv Machine Learning
Sep 1
Propensity Straight-Through Gradients for Discrete Stochastic Systems
arXiv:2608.25631v1 Announce Type: cross Abstract: Continuous-time Markov chains (CTMCs) provide the backbone for modeling discrete stochastic dynamics across applied, physical, and biological science...