Gradient-Free Sampling from Generative Models via Stochastic Bounded Extremum Seeking

arXiv:2610.04568 · stat.ML, cs.LG, math.OC, stat.CO · Submitted 2026-10-03 · Read on arXiv

stat.ML, cs.LG, math.OC, stat.CO

Submitted: 2026-10-03

Updated: 2026-10-03

Project page: https://alexscheinker.github.io/1

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes

Sources

• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors
• PhaseFlow4D: Physically Constrained 4D Beam Reconstruction via Feedback-Guided Latent Diffusion

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier