3rd Symposium on
Advances in Approximate Bayesian Inference

Virtual Event, January-February, 2021

List of papers

Papers can be found in OpenReview, where they are available for archival purposes. This does not constitute a proceedings for the symposium.

1. Roundoff Error in Metropolis-Hastings Accept-Reject Steps Video
   Matthew D. Hoffman
2. Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence
   Ghassen Jerfel, Serena Lutong Wang, Clara Fannjiang, Katherine A. Heller, Yian Ma, Michael Jordan
3. Marginal Likelihood Gradient for Bayesian Neural Networks
   Marcin B. Tomczak, Richard E. Turner
4. Decoupled Sparse Gaussian Processes Components: Separating Decision Making from Data Manifold Fitting
   Sebastian Popescu, David J. Sharp, James H. Cole, Ben Glocker
5. Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference Video
   Erik Daxberger, Eric Nalisnick, James Urquhart Allingham, Javier Antoran, José Miguel Hernández-Lobato
6. Efficient Calculation of Adversarial Examples for Bayesian Neural Networks Video
   Sina Däubener, Joel Frank, Thorsten Holz, Asja Fischer
7. Gradient-Free Adversarial Attacks for Bayesian Neural Networks Video
   Matthew Yuan, Matthew R. Wicker, Luca Laurenti
8. Generalized Posteriors in Approximate Bayesian Computation Video
   Sebastian M. Schmon, Patrick W. Cannon, Jeremias Knoblauch
9. On Batch Normalisation for Approximate Bayesian Inference
   Jishnu Mukhoti, Puneet K. Dokania, Philip Torr, Yarin Gal
10. Transforming Worlds: Automated Involutive MCMC for Open-Universe Probabilistic Models Video
    George Matheos, Alexander K. Lew, Matin Ghavamizadeh, Stuart Russell, Marco Cusumano-Towner, Vikash Mansinghka
11. Preconditioned training of normalizing flows for variational inference in inverse problems Video
    Ali Siahkoohi, Gabrio Rizzuti, Mathias Louboutin, Philipp Witte, Felix Herrmann
12. Rethinking Function-Space Variational Inference in Bayesian Neural Networks
    Tim G. J. Rudner, Zonghao Chen, Yarin Gal
13. Adaptive Strategy for Resetting a Non-stationary Markov Chain during Learning via Joint Stochastic Approximation Video
    Hyunsu Kim, Juho Lee, Hongseok Yang
14. Nested Variational Inference Video
    Heiko Zimmermann, Hao Wu, Babak Esmaeili, Sam Stites, Jan-Willem van de Meent
15. Empirical Evaluation of Biased Methods for Alpha Divergence Minimization Video
    Tomas Geffner, Justin Domke
16. The Gaussian Process Latent Autoregressive Model Video
    Rui Xia, Richard E. Turner, Wessel Bruinsma, William Tebbutt
17. Generative Video Compression as Hierarchical Variational Inference Video
    Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
18. Learning Discrete State Abstractions With Deep Variational Inference Video
    Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
19. Correlated Weights in Infinite Limits of Deep Convolutional Neural Networks Video
    Adrià Garriga-Alonso, Mark van der Wilk
20. VIB is Half Bayes Video
    Alexander A. Alemi, Warren R. Morningstar, Ben Poole, Ian Fischer, Joshua V. Dillon
21. Coupled Gradient Estimators for Discrete Latent Variables Video
    Zhe Dong, Andriy Mnih, George Tucker
22. Approximating the clusters' prior distribution in Bayesian nonparametric models Video
    Daria Bystrova, Julyan Arbel, Guillaume Kon Kam King, François Deslandes
23. Gaussian Process Latent Variable Flows for Massively Missing Data Video
    Vidhi Lalchand, Aditya Ravuri, Neil D. Lawrence
24. Distilling Ensembles Improves Uncertainty Estimates Video
    Zelda E. Mariet, Rodolphe Jenatton, Florian Wenzel, Dustin Tran
25. Evidence Estimation by Kullback-Leibler Integration for Flow-Based Methods Video
    Nikolai Zaki, Théo Galy-Fajou, Manfred Opper
26. Neural Networks as Inter-Domain Inducing Points Video
    Shengyang Sun, Jiaxin Shi, Roger B. Grosse
27. Optimal Transport Couplings of Gibbs Samplers on Partitions for Unbiased Estimation Video
    Brian Trippe, Tin D. Nguyen, Tamara Broderick
28. Exact Langevin Dynamics with Stochastic Gradients Video
    Adrià Garriga-Alonso, Vincent Fortuin
29. Expectation Programming Video
    Tim Reichelt, Adam Golinski, Luke Ong, Tom Rainforth
30. Posterior Collapse and Latent Variable Non-identifiability
    Yixin Wang, John P. Cunningham
31. Slice Sampling Reparameterization Gradients Video
    David M. Zoltowski, Diana Cai, Ryan P. Adams
32. Marginalised Spectral Mixture Kernels with Nested Sampling Video
    Fergus Simpson, Vidhi Lalchand, Carl Edward Rasmussen
33. Neural Linear Models with Functional Gaussian Process Priors Video
    Joe Watson, Jihao Andreas Lin, Pascal Klink, Jan Peters
34. Combining Pseudo-Point and State Space Approximations for Sum-Separable Gaussian Processes Video
    William Tebbutt, Arno Solin, Richard E. Turner
35. The Gaussian Neural Process Video
    Wessel Bruinsma, James Requeima, Andrew Y. K. Foong, Jonathan Gordon, Richard E. Turner
36. Annealed Stein Variational Gradient Descent Video
    Francesco D'Angelo, Vincent Fortuin
37. A Novel Regression Loss for Non-Parametric Uncertainty Optimization
    Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel
38. Variational Beam Search for Novelty Detection s Video
    Aodong Li, Alex J. Boyd, Padhraic Smyth, Stephan Mandt
39. Gradient Regularisation as Approximate Variational Inference Video
    Ali Unlu, Laurence Aitchison
40. On the Inconsistency of Bayesian Inference for Misspecified Neural Networks Video
    Yijie Zhang, Eric Nalisnick
41. Factorized Gaussian Process Variational Autoencoders Video
    Metod Jazbec, Michael A. L. Pearce, Vincent Fortuin
42. Understanding Variational Inference in Function-Space Video
    David R. Burt, Sebastian W. Ober, Adrià Garriga-Alonso, Mark van der Wilk
43. Bayesian Neural Network Priors Revisited Video
    Vincent Fortuin, Adrià Garriga-Alonso, Florian Wenzel, Gunnar Ratsch, Richard E Turner, Mark van der Wilk, Laurence Aitchison
44. Learning Discrete Distributions by Dequantization Video
    Emiel Hoogeboom, Taco Cohen, Jakub M. Tomczak
45. Conjugate Energy-Based Models Video
    Hao Wu, Babak Esmaeili, Michael L Wick, Jean-Baptiste Tristan, Jan-Willem van de Meent
46. Variational Determinant Estimation with Spherical Normalizing Flows Video
    Simon Arthur Passenheim, Emiel Hoogeboom
47. Gaussian Density Parametrization Flow: Particle and Stochastic Approaches Video
    Théo Galy-Fajou, Valerio Perrone, Manfred Opper
48. Optimal Thinning of MCMC Output Video
    Marina Riabiz, Wilson Ye Chen, Jon Cockayne, Pawel Swietach, Steven Niederer, Chris Oates
49. Why Cold Posteriors? On the Suboptimal Generalization of Optimal Bayes Estimates Video
    Chen Zeno, Itay Golan, Ari Pakman, Daniel Soudry
50. Bijective-Contrastive Estimation Video
    Jae Hyun Lim, Chin-Wei Huang, Aaron Courville, Christopher Pal
51. Self-Supervised Variational Auto-Encoders Video
    Ioannis Gatopoulos, Jakub M. Tomczak
52. Generalized Doubly-Reparameterized Gradient Estimators Video
    Matthias Bauer, Andriy Mnih
53. Sensible Priors for Bayesian Neural Networks through Wasserstein Distance Minimization to Gaussian Processes
    Ba-Hien TRAN, Dimitrios Milios, Simone Rossi, Maurizio Filippone
54. Bootstrap Ensembles as Variational Inference Video
    Dimitrios Milios, Pietro Michiardi, Maurizio Filippone
55. Argmax Flows: Learning Categorical Distributions with Normalizing Flows Video
    Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré, Max Welling
56. Scalable Hybrid Hidden Markov Model with Gaussian Process Emission for Sequential Time-series Observations Video
    Yohan Jung, Jinkyoo Park
57. HWA: Hyperparameters Weight Averaging in Bayesian Neural Networks Video
    Belhal Karimi, Ping Li
58. Ensemble sampler for infinite-dimensional inverse problems Video
    Jeremie Coullon, Robert J. Webber
59. i-DenseNets Video
    Yura Perugachi-Diaz, Jakub M. Tomczak, Sandjai Bhulai
60. Bayesian Evidential Deep Learning with PAC Regularization Video
    Manuel Haussmann, Sebastian Gerwinn, Melih Kandemir