Non-exchangeable feature allocation models with sublinear growth of the feature sizes

Mar 30, 2020
Giuseppe Di Benedetto, François Caron, Yee Whye Teh

* Accepted to AISTATS 2020 

  Access Model/Code and Paper
Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network

Mar 04, 2020
Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal


  Access Model/Code and Paper
Pruning untrained neural networks: Principles and Analysis

Feb 19, 2020
Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh

* 50 pages, 12 figures 

  Access Model/Code and Paper
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise

Feb 13, 2020
Umut Şimşekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban

* 26 pages 

  Access Model/Code and Paper
MetaFun: Meta-Learning with Iterative Functional Updates

Dec 05, 2019
Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh


  Access Model/Code and Paper
Amortized Rejection Sampling in Universal Probabilistic Programming

Nov 30, 2019
Saeid Naderiparizi, Adam Ścibior, Andreas Munk, Mehrdad Ghadiri, Atılım Güneş Baydin, Bradley Gram-Hansen, Christian Schroeder de Witt, Robert Zinkov, Philip H. S. Torr, Tom Rainforth, Yee Whye Teh, Frank Wood


  Access Model/Code and Paper
A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experiments

Nov 01, 2019
Adam Foster, Martin Jankowiak, Matthew O'Meara, Yee Whye Teh, Tom Rainforth


  Access Model/Code and Paper
Continual Unsupervised Representation Learning

Oct 31, 2019
Dushyant Rao, Francesco Visin, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu, Raia Hadsell

* NeurIPS 2019 

  Access Model/Code and Paper
Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support

Oct 29, 2019
Yuan Zhou, Hongseok Yang, Yee Whye Teh, Tom Rainforth


  Access Model/Code and Paper
Deep Amortized Clustering

Sep 30, 2019
Juho Lee, Yoonho Lee, Yee Whye Teh


  Access Model/Code and Paper
Stacked Capsule Autoencoders

Jun 17, 2019
Adam R. Kosiorek, Sara Sabour, Yee Whye Teh, Geoffrey E. Hinton

* 13 pages, 6 figures, 4 tables 

  Access Model/Code and Paper
Random Tessellation Forests

Jun 13, 2019
Shufei Ge, Shijia Wang, Yee Whye Teh, Liangliang Wang, Lloyd T. Elliott

* 10 pages, 4 figures 

  Access Model/Code and Paper
Task Agnostic Continual Learning via Meta Learning

Jun 12, 2019
Xu He, Jakub Sygnowski, Alexandre Galashov, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu


  Access Model/Code and Paper
Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality

Jun 07, 2019
Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Balaji Lakshminarayanan


  Access Model/Code and Paper
Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings

Jun 05, 2019
Jean-Francois Ton, Lucian Chan, Yee Whye Teh, Dino Sejdinovic


  Access Model/Code and Paper
Hijacking Malaria Simulators with Probabilistic Programming

May 29, 2019
Bradley Gram-Hansen, Christian Schröder de Witt, Tom Rainforth, Philip H. S. Torr, Yee Whye Teh, Atılım Güneş Baydin

* ICML Workshop on AI for Social Good, 2018 
* 6 pages, 3 figures, Accepted at the International Conference on Machine Learning AI for Social Good Workshop, Long Beach, United States, 2019 

  Access Model/Code and Paper
Meta reinforcement learning as task inference

May 15, 2019
Jan Humplik, Alexandre Galashov, Leonard Hasenclever, Pedro A. Ortega, Yee Whye Teh, Nicolas Heess


  Access Model/Code and Paper
Meta-learning of Sequential Strategies

May 08, 2019
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

* DeepMind Technical Report (15 pages, 6 figures) 

  Access Model/Code and Paper
Information asymmetry in KL-regularized RL

May 03, 2019
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess

* Accepted as a conference paper at ICLR 2019 

  Access Model/Code and Paper
Augmented Neural ODEs

Apr 02, 2019
Emilien Dupont, Arnaud Doucet, Yee Whye Teh


  Access Model/Code and Paper
Meta-Learning surrogate models for sequential decision making

Mar 28, 2019
Alexandre Galashov, Jonathan Schwarz, Hyunjik Kim, Marta Garnelo, David Saxton, Pushmeet Kohli, S. M. Ali Eslami, Yee Whye Teh


  Access Model/Code and Paper
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL

Mar 18, 2019
Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov, Leonard Hasenclever, Arun Ahuja, Greg Wayne, Razvan Pascanu, Yee Whye Teh, Nicolas Heess


  Access Model/Code and Paper
Variational Estimators for Bayesian Optimal Experimental Design

Mar 13, 2019
Adam Foster, Martin Jankowiak, Eli Bingham, Paul Horsfall, Yee Whye Teh, Tom Rainforth, Noah Goodman


  Access Model/Code and Paper
Hybrid Models with Deep and Invertible Features

Feb 07, 2019
Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Gorur, Balaji Lakshminarayanan


  Access Model/Code and Paper
Functional Regularisation for Continual Learning using Gaussian Processes

Jan 31, 2019
Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh


  Access Model/Code and Paper
Probabilistic symmetry and invariant neural networks

Jan 18, 2019
Benjamin Bloem-Reddy, Yee Whye Teh


  Access Model/Code and Paper
Hierarchical Representations with Poincaré Variational Auto-Encoders

Jan 17, 2019
Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, Yee Whye Teh


  Access Model/Code and Paper
Attentive Neural Processes

Jan 17, 2019
Hyunjik Kim, Andriy Mnih, Jonathan Schwarz, Marta Garnelo, Ali Eslami, Dan Rosenbaum, Oriol Vinyals, Yee Whye Teh


  Access Model/Code and Paper
Neural probabilistic motor primitives for humanoid control

Jan 15, 2019
Josh Merel, Leonard Hasenclever, Alexandre Galashov, Arun Ahuja, Vu Pham, Greg Wayne, Yee Whye Teh, Nicolas Heess

* Accepted as a conference paper at ICLR 2019 

  Access Model/Code and Paper