924 citations · 1.8k across the 26 of their papers we have counts for
8 papers · 1 filter
VIB is Half Bayes
Alexander A Alemi, Warren R Morningstar, Ben Poole +2
In discriminative settings such as regression and classification there are two random variables at play, the inputs X and the targets Y. Here, we demonstrate that the Variational I…
PAC-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime
Warren R. Morningstar, Alexander A. Alemi, Joshua V. Dillon
The Bayesian posterior minimizes the "inferential risk" which itself bounds the "predictive risk". This bound is tight when the likelihood and prior are well-specified. However sin…
Density of States Estimation for Out-of-Distribution Detection
Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher +3
Perhaps surprisingly, recent studies have shown probabilistic model likelihoods have poor specificity for out-of-distribution (OOD) detection and often assign higher likelihoods to…
Automatic Differentiation Variational Inference with Mixtures
Warren R. Morningstar, Sharad M. Vikram, Cusuh Ham +2
Automatic Differentiation Variational Inference (ADVI) is a useful tool for efficiently learning probabilistic models in machine learning. Generally approximate posteriors learned…
tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware
Junpeng Lao, Christopher Suter, Ian Langmore +7
Markov chain Monte Carlo (MCMC) is widely regarded as one of the most important algorithms of the 20th century. Its guarantees of asymptotic convergence, stability, and estimator-v…
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling +7
Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights. Recent work developing this class of methods…
Joint Distributions for TensorFlow Probability
Dan Piponi, Dave Moore, Joshua V. Dillon
A central tenet of probabilistic programming is that a model is specified exactly once in a canonical representation which is usable by inference algorithms. We describe JointDistr…
Hydra: Preserving Ensemble Diversity for Model Distillation
Linh Tran, Bastiaan S. Veeling, Kevin Roth +7
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory…