Search Results for author:
Found 9 papers, 1 papers with code
Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?
We prove that black-box variational inference (BBVI) with control variates, particularly the sticking-the-landing (STL) estimator, converges at a geometric (traditionally called "linear") rate under perfect variational family specification.
Monte Carlo Sampling without Isoperimetry: A Reverse Diffusion Approach
The efficacy of modern generative models is commonly contingent upon the precision of score estimation along the diffusion path, with a focus on diffusion models and their ability to generate high-quality data samples.
Black-Box Variational Inference Converges
We provide the first convergence guarantee for full black-box variational inference (BBVI), also known as Monte Carlo variational inference.
Disentangled Multi-Fidelity Deep Bayesian Active Learning
To balance quality and cost, various domain areas of science and engineering run simulations at multiple levels of sophistication.
On Optimal Early Stopping: Overparametrization versus Underparametrization
Early stopping is a simple and widely used method to prevent over-training neural networks.
Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence
We thus propose a novel combination of optimization and sampling techniques for approximate Bayesian inference by constructing an IS proposal distribution through the minimization of a forward KL (FKL) divergence.
Variational Refinement for Importance SamplingUsing the Forward Kullback-Leibler Divergence
Variational Inference (VI) is a popular alternative to asymptotically exact sampling in Bayesian inference.
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains.
Langevin Dynamics as Nonparametric Variational Inference
Variational inference (VI) and Markov chain Monte Carlo (MCMC) are approximate posterior inference algorithms that are often said to have complementary strengths, with VI being fast but biased and MCMC being slower but asymptotically unbiased.
