Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Joshua V. Dillon

PAC$^m$-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime


Oct 19, 2020
Warren R. Morningstar, Alexander A. Alemi, Joshua V. Dillon

* Submitted to AISTATS 2021 

  Access Paper or Ask Questions

Density of States Estimation for Out-of-Distribution Detection


Jun 22, 2020
Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher, Balaji Lakshminarayanan, Alexander A. Alemi, Joshua V. Dillon

* Submitted to NeurIPS. Corrected footnote from: "34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada" to "Preprint. Under review." 

  Access Paper or Ask Questions

Automatic Differentiation Variational Inference with Mixtures


Mar 05, 2020
Warren R. Morningstar, Sharad M. Vikram, Cusuh Ham, Andrew Gallagher, Joshua V. Dillon

* Submitted to UAI 2020 

  Access Paper or Ask Questions

The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks


Feb 07, 2020
Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling, Linh Tran, Joshua V. Dillon, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin


  Access Paper or Ask Questions

tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware


Feb 04, 2020
Junpeng Lao, Christopher Suter, Ian Langmore, Cyril Chimisov, Ashish Saxena, Pavel Sountsov, Dave Moore, Rif A. Saurous, Matthew D. Hoffman, Joshua V. Dillon

* Based on extended abstract submitted to PROBPROG 2020 

  Access Paper or Ask Questions

Joint Distributions for TensorFlow Probability


Jan 22, 2020
Dan Piponi, Dave Moore, Joshua V. Dillon

* Based on extended abstract submitted to PROBPROG 2020 

  Access Paper or Ask Questions

Hydra: Preserving Ensemble Diversity for Model Distillation


Jan 14, 2020
Linh Tran, Bastiaan S. Veeling, Kevin Roth, Jakub Swiatkowski, Joshua V. Dillon, Jasper Snoek, Stephan Mandt, Tim Salimans, Sebastian Nowozin, Rodolphe Jenatton


  Access Paper or Ask Questions

Likelihood Ratios for Out-of-Distribution Detection


Jun 07, 2019
Jie Ren, Peter J. Liu, Emily Fertig, Jasper Snoek, Ryan Poplin, Mark A. DePristo, Joshua V. Dillon, Balaji Lakshminarayanan


  Access Paper or Ask Questions

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift


Jun 06, 2019
Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D Sculley, Sebastian Nowozin, Joshua V. Dillon, Balaji Lakshminarayanan, Jasper Snoek


  Access Paper or Ask Questions

NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport


Mar 09, 2019
Matthew Hoffman, Pavel Sountsov, Joshua V. Dillon, Ian Langmore, Dustin Tran, Srinivas Vasudevan


  Access Paper or Ask Questions

Uncertainty in the Variational Information Bottleneck


Jul 02, 2018
Alexander A. Alemi, Ian Fischer, Joshua V. Dillon

* 10 pages, 7 figures. Accepted to UAI 2018 - Uncertainty in Deep Learning Workshop 

  Access Paper or Ask Questions

Fixing a Broken ELBO


Feb 13, 2018
Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy

* 21 pages, 9 figures 

  Access Paper or Ask Questions

TensorFlow Distributions


Nov 28, 2017
Joshua V. Dillon, Ian Langmore, Dustin Tran, Eugene Brevdo, Srinivas Vasudevan, Dave Moore, Brian Patton, Alex Alemi, Matt Hoffman, Rif A. Saurous


  Access Paper or Ask Questions

Deep Variational Information Bottleneck


Jul 17, 2017
Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, Kevin Murphy

* 19 pages, 8 figures, Accepted to ICLR17 

  Access Paper or Ask Questions