Search Results for author:
Found 6 papers, 3 papers with code
Solving Bayesian inverse problems with diffusion priors and off-policy RL
This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (RL) objective that can asymptotically solve Bayesian inverse problems optimally.
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
We propose to amortize the cost of sampling from such posterior distributions with diffusion models that sample a distribution in the noise space ($\mathbf{z}$).
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences.
Amortizing intractable inference in diffusion models for vision, language, and control
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem.
Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space
To improve scalability for larger models, one common Bayesian approach is to approximate the global predictive posterior by multiplying local predictive posteriors.
Robust One Round Federated Learning with Predictive Space Bayesian Inference
In contrast, our method performs the aggregation on the predictive posteriors, which are typically easier to approximate owing to the low-dimensionality of the output space.
