On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network Posteriors.
Tim RensmeyerOliver NiggemannPublished in: CoRR (2024)
Keyphrases
- locally adaptive
- sampling methods
- neural network
- posterior distribution
- random sampling
- bayesian inference
- posterior probability
- class imbalance
- sampling algorithm
- subband
- hyperparameters
- bayesian networks
- probability distribution
- multiscale
- knn
- bayesian framework
- cost sensitive
- latent variables
- original data
- parameter estimation
- image compression
- probabilistic model
- active learning
- image processing