Schedule & Accepted Papers
Slides for invited talks are now online (see [slides] below), as well as workshop video recordings.
Confirmed Speakers
Schedule
8.00 - 8.05 | Opening remarks | ||
8.05 - 8.25 | Invited talk | Alexander G. de G. Matthews (DeepMind) [slides] | Gaussian Process Behaviour in Wide Deep Neural Networks |
8.25 - 8.40 | Contributed talk | Tim G. J. Rudner, Florian Wenzel and Yarin Gal | The Natural Neural Tangent Kernel: Neural Network Training Dynamics under Natural Gradient Descent |
8.40 - 9.00 | Invited talk | Yingzhen Li (Microsoft Research) [slides] | On estimating epistemic uncertainty (tentative) |
9.00 - 9.15 | Contributed talk | Stanislav Fort, Huiyi Hu and Balaji Lakshminarayanan | Deep Ensembles: A Loss Landscape Perspective |
9.15 - 9.30 | Poster spotlights | ||
9.30 - 10.30 | Discussion over coffee and poster session | ||
10.30 - 10.50 | Invited talk | Andrew Gordon Wilson (NYU) [slides] | Using Loss Surface Geometry for Scalable Bayesian Deep Learning |
10.50 - 11.05 | Contributed talk | Abhishek Kumar and Ben Poole | On Implicit Regularization in β-VAE |
11.05 - 11.25 | Invited talk | Jasper Snoek (Google) [slides] | Uncertainty under distributional shift |
11.25 - 11.40 | Contributed talk | Sicong Huang, Alireza Makhzani, Yanshuai Cao and Roger Grosse | Evaluating Lossy Compression Rates of Deep Generative Models |
11.40 - 13.20 | Lunch | ||
13.20 - 13.40 | Invited talk | Chelsea Finn (Google Brain / Berkeley / Stanford) [slides] | The Big Problem with Meta-Learning and How Bayesians Can Fix It |
13.40 - 13.55 | Contributed talk | Riccardo Moriconi, Marc Peter Deisenroth and Senanayak Sesh Kumar Karri | High-dimensional Bayesian optimization using low-dimensional feature spaces |
13.55 - 14.15 | Invited talk | Roger Grosse (Toronto) [slides] | Functional variational Bayesian neural networks |
14.15 - 14.30 | Contributed talk | Sebastian Farquhar, Lewis Smith and Yarin Gal | Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Variational Inference in Deep Networks |
14.30 - 15.30 | Discussion over coffee and poster session | ||
15.30 - 15.45 | Contributed talk | Andrew Ross, Jianzhun Du, Yonadav Shavit and Finale Doshi-Velez | Controlled Direct Effect Priors for Bayesian Neural Networks |
15.45 - 16.05 | Invited talk | Debora Marks (Harvard Medical School / Broad Institute) [slides] | Deep generative models for genetic variation and drug design |
16.05 - 16.20 | Contributed talk | Mihaela Rosca, Michael Figurnov, Shakir Mohamed and Andriy Mnih | Measure Valued Derivatives for Approximate Bayesian Inference |
16.20 - 17.30 | Panel Session | Panellists: Debora Marks Jasper Snoek Chelsea Finn Andrew Gordon Wilson Yingzhen Li Roger Grosse Alexander G. de G. Matthews Moderator: Finale Doshi-Velez |
|
17.30 - 19.30 | Poster session |
Accepted Abstracts
We added all camera ready submissions sent to us by 11/12/2019. If a paper is not online, please contact the lead author and encourage them to send us the camera ready.
Authors | Title |
Andrew Y. K. Foong, David R. Burt, Yingzhen Li and Richard E. Turner | Pathologies of Factorised Gaussian and MC Dropout Posteriors in Bayesian Neural Networks [paper] |
Paulo Rauber, Aditya Ramesh and Jürgen Schmidhuber | Recurrent neural-linear posterior sampling for non-stationary bandits [paper] |
Andreas Look and Melih Kandemir | Differential Bayesian Neural Nets [paper] |
Matt Benatan and Edward Pyzer-Knapp | Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning [paper] |
Ruiyi Zhang, Changyou Chen, Zhe Gan, Zheng Wen and Lawrence Carin | Nested-Wasserstein Self-Imitation Learning for Sequence Generation [paper] |
Marton Havasi, Jasper Snoek, Dustin Tran, Jonathan Gordon and Jose Miguel Hernandez-Lobato | Refining the variational posterior through iterative optimization [paper] |
Hlynur Jonsson, Giovanni Cherubini and Evangelos Eleftheriou | Convergence of DNNs with mutual-information-based regularization [paper] |
Fredrik K. Gustafsson, Martin Danelljan and Thomas B. Schön | Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision [paper] |
Angelos Filos, Sebastian Farquhar, Aidan N. Gomez, Tim G. J. Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroon and Yarin Gal | A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks [paper] |
James Brofos, Rui Shu and Roy Lederman | A Bias-Variance Decomposition for Bayesian Deep Learning [paper] |
Nabeel Seedat and Christopher Kanan | Towards calibrated and scalable uncertainty representations for neural networks [paper] |
Otmane Sakhi, Stephen Bonner, David Rohde and Flavian Vasile | Reconsidering analytical variational bounds for output layers of deep networks [paper] |
Micha Livne, Kevin Swersky and David Fleet | High Mutual Information in Representation Learning with Symmetric Variational Inference [paper] |
Hao Fu, Chunyuan Li, Ke Bai, Jianfeng Gao and Lawrence Carin | Flexible Text Modeling withSemi-Implicit Latent Representations [paper] |
Suwen Lin, Martin Wistuba, Ambrish Rawat and Nitesh Chawla | Neural Tree Kernel Learning [paper] |
Ivan Ustyuzhaninov, Ieva Kazlauskaite, Markus Kaiser, Erik Bodin, Carl Henrik Ek and Neill Campbell | Compositional uncertainty in deep Gaussian processes [paper] |
Adam D Cobb, Atilim Günes Baydin, Ivan Kiskin, Andrew Markham and Stephen Roberts | Semi-separable Hamiltonian Monte Carlo for inference in Bayesian neural networks [paper] |
Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh and Balaji Lakshminarayanan | Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality [paper] |
Felix McGregor, Arnu Pretorius, Johan du Preez and Steve Kroon | Stabilising priors for robust Bayesian deep learning [paper] |
John Moberg, Lennart Svensson, Juliano Pinto and Henk Wymeersch | Bayesian Linear Regression on Deep Representations [paper] |
Bang An, Xuannan Dong and Changyou Chen | Repulsive Bayesian Sampling for Diversified Attention Modeling [paper] |
Colin White, Willie Neiswanger and Yash Savani | Deep Uncertainty Estimation for Model-based Neural Architecture Search [paper] |
Vincent Fortuin and Gunnar Rätsch | Deep Mean Functions for Meta-Learning in Gaussian Processes [paper] |
Anirudh Suresh and Srivatsan Srinivasan | Improved Attentive Neural Processes [paper] |
Patrick McClure, Nao Rho, John Lee, Jakub Kaczmarzyk, Charles Zheng, Satrajit Ghosh, Dylan Nielson, Adam Thomas, Peter Bandettini and Francisco Pereira | Improving 3D Brain Segmentation using a Spike-and-Slab Bayesian Deep Neural Network [paper] |
Tim R. Davidson, Jakub M. Tomczak and Efstratios Gavves | Increasing Expressivity of a Hyperspherical VAE [paper] |
Gaurush Hiranandani, Sumeet Katariya, Nikhil Rao and Karthik Subbian | Online Bayesian Learning for E-Commerce Query Reformulation [paper] |
Sanjeev Arora, Simon Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang and Dingli Yu | On the Power of NTK on Small Data [paper] |
Prithvijit Chakrabarty and Subhransu Maji | The Spectral Bias of the Deep Image Prior [paper] |
Masha Itkina, Boris Ivanovic, Ransalu Senanayake, Mykel Kochenderfer and Marco Pavone | Evidential Disambiguation of Latent Multimodality in Conditional Variational Autoencoders [paper] |
Simone Rossi, Sébastien Marmin and Maurizio Filippone | Efficient Approximate Inference with Walsh-Hadamard Variational Inference [paper] |
Didrik Nielsenand Ole Winther | PixelCNN as a Single-Layer Flow [paper] |
Changyong Oh, Kamil Adamczewski and Mijung Park | The Radial and Directional Posteriors for Bayesian Deep Learning [paper] |
William Harvey, Michael Teng and Frank Wood | Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks [paper] |
Matias Valdenegro-Toro | Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification [paper] |
Stefano Peluchetti and Stefano Favaro | Neural SDE - Information propagation through the lens of diffusion processes [paper] |
Riccardo Moriconi, Marc Peter Deisenroth and Senanayak Sesh Kumar Karri | High-dimensional Bayesian optimization using low-dimensional feature spaces [paper] |
Ali Hebbal, Loic Brevault, Mathieu Balesdent, El-Ghazali Talbi and Nouredine Melab | Multi-fidelity modeling using DGPs: Improvements and a generalization to varying input space dimensions [paper] |
Wen Yao, Jun Zhang, Qiang Chang, Xiaozhou Zhu and Weien Zhou | Error Estimation of Sampling-free Uncertainty Propagation in Bayesian Neural Network with Simplified Covariance Matrix [paper] |
Sebastian Farquhar, Lewis Smith and Yarin Gal | Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Variational Inference in Deep Networks [paper] |
Tianyu Cui, Pekka Marttinen and Samuel Kaski | Learning Global Pairwise Interactions with Bayesian Neural Networks [paper] |
Da Tang, Dawen Liang, Nicholas Ruozzi and Tony Jebara | Learning Correlated Latent Representations with Adaptive Priors [paper] |
Vaclav Smidl, Jan Bim and Tomas Pevny | Orthogonal Approximation of Marginal Likelihood of Generative Models [paper] |
Augustin Prado, Ravinath Kausik and Lalitha Venkataramanan | Dual Neural Network Architecture for Determining Epistemic and Aleatoric Uncertainties [paper] |
Chunlin Ji and Haige Shen | Stochastic Variational Inference via Upper Bound [paper] |
Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham and Pushmeet Kohli | Learning Perturbation-Invariant Representations with Smooth Encoders [paper] |
Jack Fitzsimons, Sebastian Schmon and Stephen Roberts | Implicit Priors for Knowledge Sharing in Bayesian Neural Networks [paper] |
Mike Wu, Kristy Choi, Noah Goodman and Stefano Ermon | Meta-Amortized Variational Inference and Learning [paper] |
He Zhao, Piyush Rai, Lan Du, Wray Buntine, Dinh Phung and Mingyuan Zhou | A Bayesian Extension to VAEs for Discrete Data [paper] |
Agustinus Kristiadi, Sina Däubener and Asja Fischer | Uncertainty quantification with compound density networks [paper] |
Niklas Heim, Václav Šmídl and Tomáš Pevný | Rodent: Relevance determination in ODE [paper] |
Kathrin Grosse, David Pfaff, Michael T. Smith and Michael Backes | The Limitations of Model Uncertainty in Adversarial Settings [paper] |
Timon Willi, Jonathan Masci, Jürgen Schmidhuber and Christian Osendorfer | Recurrent Neural Processes [paper] |
Samuel Kessler, Vu Nguyen, Stefan Zohren and Steve Roberts | Indian Buffet Neural Networks for Continual Learning [paper] |
Mariana Vargas Vieyra, Aurélien Bellet and Pascal Denis | Probabilistic End-to-End Graph-based Semi-Supervised Learning [paper] |
Apratim Bhattacharyya, Mario Fritz and Bernt Schiele | “Best of Many” Samples Distribution Matching [paper] |
Apratim Bhattacharyya, Michael Hanselmann, Mario Fritz, Bernt Schiele and Christoph-Nikolas Straehle | Conditional Flow Variational Autoencoders for Structured Sequence Prediction [paper] |
Rahul Sharma, Abhishek Kumar and Piyush Rai | Refined $\alpha$-Divergence Variational Inference via Rejection Sampling [paper] |
Luis A. Perez Rey, Vlado Menkovski and Jacobus W. Portegies | Can VAEs capture topological properties? [paper] |
Geoffroy Dubourg-Felonneau, Omar Darwish, Christopher Parsons, Dàmi Rebergen, John Cassidy, Nirmesh Patel and Harry Clifford | Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer [paper] |
Jonathan Warrell and Mark Gerstein | Hierarchical PAC-Bayes Bounds via Deep Probabilistic Programming [paper] |
Slava Voloshynovskiy, Mouad Kondah, Shideh Rezaeifar, Olga Taran, Taras Holotyak and Danilo J. Rezende | Information bottleneck through variational glasses [paper] |
Mihaela Rosca, Michael Figurnov, Shakir Mohamed and Andriy Mnih | Measure Valued Derivatives for Approximate Bayesian Inference [paper] |
Max-Heinrich Laves, Sontje Ihler, Karl-Philipp Kortmann and Tobias Ortmaier | Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference [paper] |
Matthew Willetts, Stephen Roberts and Chris Holmes | Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders [paper] |
Jiaming Song and Stefano Ermon | Mutual Information Estimation as Optimization over Density Ratios: A Unifying Perspective [paper] |
Andrew Ross, Jianzhun Du, Yonadav Shavit and Finale Doshi-Velez | Controlled Direct Effect Priors for Bayesian Neural Networks [paper] |
Yeming Wen, Dustin Tran and Jimmy Ba | BatchEnsemble: Efficient Ensemble of Deep Neural Networks via Rank-1 Perturbation [paper] |
Homa Fashandi and Darin Graham | Empirical Studies on Sensitivity to Perturbations and Hyperparameters in Bayesian Neural Networks [paper] |
Ruiqi Gao, Erik Nijkamp, Zhen Xu, Andrew Dai, Diederik Kingma and Ying Nian Wu | Flow Contrastive Estimation of Energy-Based Model [paper] |
Hooshmand Shokri Razaghi and Liam Paninski | Filtering Normalizing Flows [paper] |
Joshua Chang, Shashaank Vattikuti and Carson Chow | Probabilistically-autoencoded horseshoe-disentangled multidomain item-response theory models [paper] |
Tim Xiao, Aidan Gomez and Yarin Gal | Wat heb je gezegd? Detecting Out-of-Distribution Translations with Variational Transformers [paper] |
Vanessa Boehm, Francois Lanusse and Uros Seljak | Uncertainty Quantification with Generative Models [paper] |
Giorgio Giannone, Christian Osendorfer and Jonathan Masci | No Representation without Transformation [paper] |
Gintare Karolina Dziugaite, Waseem Gharbieh, Kyle Hsu and Daniel Roy | Optimal (PAC-Bayes) priors are data dependent [paper] |
Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo, Angelos Filos and Yarin Gal | Improving MFVI in Bayesian Neural Networks with Empirical Bayes: a Study with Diabetic Retinopathy Diagnosis [paper] |
Ari Heljakka, Yuxin Hou, Juho Kannala and Arno Solin | Conditional Image Sampling by Deep Automodulators [paper] |
Joe Davison, Kristen Severson and Soumya Ghosh | Cross-population Variational Autoencoders [paper] |
Arsenii Ashukha, Alexander Lyzhov, Dmitry Molchanov and Dmitry Vetrov | Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning [paper] |
Jeremiah Liu | Variable Selection with Rigorous Uncertainty Quantification using Bayesian Deep Neural Networks [paper] |
Sicong Huang, Alireza Makhzani, Yanshuai Cao and Roger Grosse | Evaluating Lossy Compression Rates of Deep Generative Models [paper] |
Dian Ang Yap, Nicholas Roberts and Vinay Prabhu | Grassmannian Packings in Neural Networks: Learning with Maximal Subspace Packings for Diversity and Anti-Sparsity [paper] |
Evgenii Nikishin, Arsenii Ashukha and Dmitry Vetrov | Unsupervised Domain Adaptation with Shared Latent Dynamics for Reinforcement Learning [paper] |
Imant Daunhawer, Thomas Sutter and Julia E. Vogt | Improving Multimodal Generative Models with Disentangled Latent Partitions [paper] |
Sunho Park, Saehoon Kim, Hongming Xu and Tae Hyun Hwang | Deep Gaussian processes for weakly supervised learning: tumor mutation burden (TMB) prediction [paper] |
Nilesh Ahuja, Ibrahima Ndiour, Trushant Kalyanpur and Omesh Tickoo | Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection [paper] |
Stanislav Fort, Huiyi Hu and Balaji Lakshminarayanan | Deep Ensembles: A Loss Landscape Perspective [paper] |
Abhishek Kumar and Ben Poole | On Implicit Regularization in β-VAE [paper] |
Steindor Saemundsson, Katja Hofmann and Marc Deisenroth | Variational Integrator Networks [paper] |
Mahesh Subedar, Nilesh Ahuja, Ranganath Krishnan, Ibrahima Ndiour and Omesh Tickoo | Deep Probabilistic Models to Detect Data Poisoning Attacks [paper] |
Roman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Jascha Sohl-Dickstein and Samuel Schoenholz | Neural Tangents: Easy and Fast Infinite Networks in Python [paper] |
Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto and Dmitry Vetrov | Low-variance Gradient Estimates for the Plackett-Luce Distribution [paper] |
Jhosimar Arias Figueroa | Semi-supervised Learning using Deep Generative Models and Auxiliary Tasks [paper] |
Erik Daxberger and José Miguel Hernández-Lobato | Bayesian VAEs for Unsupervised Anomaly Detection [paper] |
Xavier Gitiaux, Shane Maloney, Anna Jungbluth, Carl Shneider, Atılım Güneş Baydin, Paul J. Wright, Yarin Gal, Michel Deudon, Alfredo Kalaitzis and Andres Munoz-Jaramillo | Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties [paper] |
Tim G. J. Rudner, Florian Wenzel and Yarin Gal | The Natural Neural Tangent Kernel: Neural Network Training Dynamics under Natural Gradient Descent [paper] |
Waseem Aslam, Tim G. J. Rudner and Yarin Gal | Tighter Variational Bounds for Deep Gaussian Processes [paper] |
Adrián Csiszárik, Beatrix Benkő and Dániel Varga | Negative Sampling in Variational Autoencoders [paper] |
Aditya Grover, Dustin Tran, Rui Shu, Ben Poole and Kevin Murphy | Probing Uncertainty Estimates of Neural Processes [paper] |