Uncertainty
Consistency Diffusion Bridge Models Guande He
Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data.
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Current uncertainty quantification is memory and compute expensive, which hinders practical uptake.
Approximation-Aware Bayesian Optimization
Our approach can be used with any decision-theoretic acquisition function and is readily compatible with trust region methods like TuRBO.
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
The premise of semi-supervised learning (SSL) is that combining labeled and unlabeled data yields significantly more accurate models.
DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transform
Most recent approaches are motivated heuristically and lack a unifying framework, obscuring connections between them. Further, they often suffer from issues such as being very sensitive to hyperparameters, being expensive to train or needing access to weights hidden behind a closed API.
