posterior sampling
In Bayesian inference, posterior sampling involves drawing samples from the posterior distribution of a model's parameters given the data. It allows for making probabilistic predictions and understanding uncertainty in model predictions.
- From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
- Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
- InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
- Multitask Learning with Stochastic Interpolants
- Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
- Self-diffusion for Solving Inverse Problems
- Split Gibbs Discrete Diffusion Posterior Sampling
- Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
- Steering Generative Models with Experimental Data for Protein Fitness Optimization