Uncertainty
Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
Conditional sampling is an essential primitive in the machine learning toolkit.
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network Anonymous Author(s) Affiliation Address email
We show that our "Joint Structure and
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network Tristan Deleu
In addition to being a challenging problem due to the super-exponentially large search space, learning a single DAG structure from data may also lead to confident but incorrect predictions (Madigan et al.,
Riemannian Laplace approximations for Bayesian neural networks
However, practical posteriors are often, even locally, highly non-Gaussian, and empirical performance deteriorates.
Assessing Causal Reasoning in Language Models
The ability to perform causal reasoning is widely considered a core feature of intelligence.
Real-World Image Variation by Aligning Diffusion Inversion Chain - Appendix Anonymous Author(s) Affiliation Address email
Bayes' theorem could be applied to approximate
Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick
Our first contribution addresses this shortcoming by introducing the CatLog-Derivative trick-a variation of the Log-Derivative trick tailored towards categorical distributions.