
Continual Unsupervised Representation Learning
Continual learning aims to improve the ability of modern learning system...
10/31/2019 ∙ by Dushyant Rao, et al. ∙ 52 ∙ shareread it

Deep Amortized Clustering
We propose a deep amortized clustering (DAC), a neural architecture whic...
09/30/2019 ∙ by Juho Lee, et al. ∙ 30 ∙ shareread it

A Unified Stochastic Gradient Approach to Designing BayesianOptimal Experiments
We introduce a fully stochastic gradient based approach to Bayesian opti...
11/01/2019 ∙ by Adam Foster, et al. ∙ 23 ∙ shareread it

MetaLearning surrogate models for sequential decision making
Metalearning methods leverage past experience to learn datadriven indu...
03/28/2019 ∙ by Alexandre Galashov, et al. ∙ 22 ∙ shareread it

Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
Universal probabilistic programming systems (PPSs) provide a powerful an...
10/29/2019 ∙ by Yuan Zhou, et al. ∙ 21 ∙ shareread it

Exploiting Hierarchy for Learning and Transfer in KLregularized RL
As reinforcement learning agents are tasked with solving more challengin...
03/18/2019 ∙ by Dhruva Tirumala, et al. ∙ 20 ∙ shareread it

On Exploration, Exploitation and Learning in Adaptive Importance Sampling
We study adaptive importance sampling (AIS) as an online learning proble...
10/31/2018 ∙ by Xiaoyu Lu, et al. ∙ 16 ∙ shareread it

Augmented Neural ODEs
We show that Neural Ordinary Differential Equations (ODEs) learn represe...
04/02/2019 ∙ by Emilien Dupont, et al. ∙ 16 ∙ shareread it

Metalearning of Sequential Strategies
In this report we review memorybased metalearning as a tool for buildi...
05/08/2019 ∙ by Pedro A. Ortega, et al. ∙ 16 ∙ shareread it

Variational Estimators for Bayesian Optimal Experimental Design
Bayesian optimal experimental design (BOED) is a principled framework fo...
03/13/2019 ∙ by Adam Foster, et al. ∙ 16 ∙ shareread it

Functional Regularisation for Continual Learning using Gaussian Processes
We introduce a novel approach for supervised continual learning based on...
01/31/2019 ∙ by Michalis K. Titsias, et al. ∙ 14 ∙ shareread it

MetaFun: MetaLearning with Iterative Functional Updates
Fewshot supervised learning leverages experience from previous learning...
12/05/2019 ∙ by Jin Xu, et al. ∙ 13 ∙ shareread it

Neural probabilistic motor primitives for humanoid control
We focus on the problem of learning a single motor module that can flexi...
11/28/2018 ∙ by Josh Merel, et al. ∙ 12 ∙ shareread it

Hybrid Models with Deep and Invertible Features
We propose a neural hybrid model consisting of a linear model defined on...
02/07/2019 ∙ by Eric Nalisnick, et al. ∙ 12 ∙ shareread it

Amortized Rejection Sampling in Universal Probabilistic Programming
Existing approaches to amortized inference in probabilistic programs wit...
10/20/2019 ∙ by Saeid Naderiparizi, et al. ∙ 11 ∙ shareread it

Set Transformer
Many machine learning tasks such as multiple instance learning, 3D shape...
10/01/2018 ∙ by Juho Lee, et al. ∙ 10 ∙ shareread it

Probabilistic symmetry and invariant neural networks
In an effort to improve the performance of deep neural networks in data...
01/18/2019 ∙ by Benjamin BloemReddy, et al. ∙ 10 ∙ shareread it

Attentive Neural Processes
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by le...
01/17/2019 ∙ by Hyunjik Kim, et al. ∙ 10 ∙ shareread it

Neural Processes
A neural network (NN) is a parameterised function that can be tuned via ...
07/04/2018 ∙ by Marta Garnelo, et al. ∙ 6 ∙ shareread it

Do Deep Generative Models Know What They Don't Know?
A neural network deployed in the wild may be asked to make predictions f...
10/22/2018 ∙ by Eric Nalisnick, et al. ∙ 6 ∙ shareread it

Disentangling Disentanglement
We develop a generalised notion of disentanglement in Variational AutoE...
12/06/2018 ∙ by Emile Mathieu, et al. ∙ 6 ∙ shareread it

Information asymmetry in KLregularized RL
Many real world tasks exhibit rich structure that is repeated across dif...
05/03/2019 ∙ by Alexandre Galashov, et al. ∙ 6 ∙ shareread it

Noise Contrastive MetaLearning for Conditional Density Estimation using Kernel Mean Embeddings
Current metalearning approaches focus on learning functional representa...
06/05/2019 ∙ by JeanFrancois Ton, et al. ∙ 6 ∙ shareread it

Meta reinforcement learning as task inference
Humans achieve efficient learning by relying on prior knowledge about th...
05/15/2019 ∙ by Jan Humplik, et al. ∙ 5 ∙ shareread it

Detecting OutofDistribution Inputs to Deep Generative Models Using a Test for Typicality
Recent work has shown that deep generative models can assign higher like...
06/07/2019 ∙ by Eric Nalisnick, et al. ∙ 5 ∙ shareread it

Random Tessellation Forests
Space partitioning methods such as random forests and the Mondrian proce...
06/13/2019 ∙ by Shufei Ge, et al. ∙ 5 ∙ shareread it

Sampling and Inference for Beta NeutraltotheLeft Models of Sparse Networks
Empirical evidence suggests that heavytailed degree distributions occur...
07/09/2018 ∙ by Benjamin BloemReddy, et al. ∙ 4 ∙ shareread it

Hijacking Malaria Simulators with Probabilistic Programming
Epidemiology simulations have become a fundamental tool in the fight aga...
05/29/2019 ∙ by Bradley GramHansen, et al. ∙ 4 ∙ shareread it

Stacked Capsule Autoencoders
An object can be seen as a geometrically organized set of interrelated p...
06/17/2019 ∙ by Adam R. Kosiorek, et al. ∙ 4 ∙ shareread it

Mix&Match  Agent Curricula for Reinforcement Learning
We introduce Mix&Match (M&M)  a training framework designed to facilita...
06/05/2018 ∙ by Wojciech Marian Czarnecki, et al. ∙ 2 ∙ shareread it

Controllable Semantic Image Inpainting
We develop a method for usercontrollable semantic image inpainting: Giv...
06/15/2018 ∙ by Jin Xu, et al. ∙ 2 ∙ shareread it

Conditional Neural Processes
Deep neural networks excel at function approximation, yet they are typic...
07/04/2018 ∙ by Marta Garnelo, et al. ∙ 2 ∙ shareread it

Inference Trees: Adaptive Inference with Exploration
We introduce inference trees (ITs), a new class of inference methods tha...
06/25/2018 ∙ by Tom Rainforth, et al. ∙ 2 ∙ shareread it

Distral: Robust Multitask Reinforcement Learning
Most deep reinforcement learning algorithms are data inefficient in comp...
07/13/2017 ∙ by Yee Whye Teh, et al. ∙ 0 ∙ shareread it

Scaling up the Automatic Statistician: Scalable Structure Discovery using Gaussian Processes
Automating statistical modelling is a challenging problem that has farr...
06/08/2017 ∙ by Hyunjik Kim, et al. ∙ 0 ∙ shareread it

Filtering Variational Objectives
When used as a surrogate objective for maximum likelihood estimation in ...
05/25/2017 ∙ by Chris J. Maddison, et al. ∙ 0 ∙ shareread it

Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata
We combine finegrained spatially referenced census data with the vote o...
11/11/2016 ∙ by Seth Flaxman, et al. ∙ 0 ∙ shareread it

Gaussian Processes for Survival Analysis
We introduce a semiparametric Bayesian model for survival analysis. The...
11/02/2016 ∙ by Tamara Fernández, et al. ∙ 0 ∙ shareread it

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
The reparameterization trick enables optimizing large scale stochastic c...
11/02/2016 ∙ by Chris J. Maddison, et al. ∙ 0 ∙ shareread it

A nonparametric HMM for genetic imputation and coalescent inference
Genetic sequence data are well described by hidden Markov models (HMMs) ...
11/02/2016 ∙ by Lloyd T. Elliott, et al. ∙ 0 ∙ shareread it

Poisson intensity estimation with reproducing kernels
Despite the fundamental nature of the inhomogeneous Poisson process in t...
10/27/2016 ∙ by Seth Flaxman, et al. ∙ 0 ∙ shareread it

Relativistic Monte Carlo
Hamiltonian Monte Carlo (HMC) is a popular Markov chain Monte Carlo (MCM...
09/14/2016 ∙ by Xiaoyu Lu, et al. ∙ 0 ∙ shareread it

Faithful Model Inversion Substantially Improves Autoencoding Variational Inference
In learning deep generative models, the encoder for variational inferenc...
12/01/2017 ∙ by Stefan Webb, et al. ∙ 0 ∙ shareread it

A characterization of productform exchangeable feature probability functions
We characterize the class of exchangeable feature allocations assigning ...
07/07/2016 ∙ by Marco Battiston, et al. ∙ 0 ∙ shareread it

Bayesian nonparametrics for Sparse Dynamic Networks
We propose a Bayesian nonparametric prior for timevarying networks. To ...
07/06/2016 ∙ by Konstantina Palla, et al. ∙ 0 ∙ shareread it

The Mondrian Kernel
We introduce the Mondrian kernel, a fast random feature approximation to...
06/16/2016 ∙ by Matej Balog, et al. ∙ 0 ∙ shareread it

Collaborative Filtering with Side Information: a Gaussian Process Perspective
We tackle the problem of collaborative filtering (CF) with side informat...
05/23/2016 ∙ by Hyunjik Kim, et al. ∙ 0 ∙ shareread it

DRABC: Approximate Bayesian Computation with KernelBased Distribution Regression
Performing exact posterior inference in complex generative models is oft...
02/15/2016 ∙ by Jovana Mitrovic, et al. ∙ 0 ∙ shareread it

Distributed Bayesian Learning with Stochastic Naturalgradient Expectation Propagation and the Posterior Server
This paper makes two contributions to Bayesian machine learning algorith...
12/31/2015 ∙ by Leonard Hasenclever, et al. ∙ 0 ∙ shareread it

Expectation Particle Belief Propagation
We propose an original particlebased implementation of the Loopy Belief...
06/19/2015 ∙ by Thibaut Lienart, et al. ∙ 0 ∙ shareread it
Yee Whye Teh
is this you? claim profile
Professorial Research Fellow (RSIV) of Statistical Machine Learning at University of Oxford