
A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging
Machine learning models commonly exhibit unexpected failures postdeploy...
read it

Interpreting diffusion score matching using normalizing flow
Scoring matching (SM), and its related counterpart, Stein discrepancy (S...
read it

Active Slices for Sliced Stein Discrepancy
Sliced Stein discrepancy (SSD) and its kernelized variants have demonstr...
read it

Combining Deep Generative Models and Multilingual Pretraining for Semisupervised Document Classification
Semisupervised learning through deep generative models and multilingua...
read it

Reinforcement Learning with Efficient Active Feature Acquisition
Solving reallife sequential decision making problems under partial obse...
read it

A Study on Efficiency in Continual Learning Inspired by Human Learning
Humans are efficient continual learning systems; we continually learn ne...
read it

Hierarchical Sparse Variational Autoencoder for Text Encoding
In this paper we focus on unsupervised representation learning and propo...
read it

Interpreting Spatially Infinite Generative Models
Traditional deep generative models of images and other spatial modalitie...
read it

MetaLearning for Variational Inference
Variational inference (VI) plays an essential role in approximate Bayesi...
read it

Sliced Kernelized Stein Discrepancy
Kernelized Stein discrepancy (KSD), though being extensively used in goo...
read it

A Causal View on Robustness of Neural Networks
We present a causal view on the robustness of neural networks against in...
read it

Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
Recent work has shown the ability to learn generative models for 3D shap...
read it

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
The ability for policies to generalize to new environments is key to the...
read it

On the Importance of the KullbackLeibler Divergence Term in Variational Autoencoders for Text Generation
Variational Autoencoders (VAEs) are known to suffer from learning uninfo...
read it

Pathologies of Factorised Gaussian and MC Dropout Posteriors in Bayesian Neural Networks
Neural networks provide stateoftheart performance on a variety of tas...
read it

'InBetween' Uncertainty in Bayesian Neural Networks
We describe a limitation in the expressiveness of the predictive uncerta...
read it

Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care
Clinical decision making is challenging because of pathological complexi...
read it

MetaLearning for Stochastic Gradient MCMC
Stochastic gradient Markov chain Monte Carlo (SGMCMC) has become increa...
read it

Variational Implicit Processes
This paper introduces the variational implicit processes (VIPs), a Bayes...
read it

A Deep Generative Model for Disentangled Representations of Sequential Data
We present a VAE architecture for encoding and generating high dimension...
read it

Are Generative Classifiers More Robust to Adversarial Attacks?
There is a rising interest in studying the robustness of deep neural net...
read it

Variational Continual Learning
This paper develops variational continual learning (VCL), a simple but g...
read it

Gradient Estimators for Implicit Models
Implicit models, which allow for the generation of samples but not for p...
read it

Dropout Inference in Bayesian Neural Networks with Alphadivergences
To obtain uncertainty estimates with realworld Bayesian deep learning m...
read it

Approximate Inference with Amortised MCMC
We propose a novel approximate inference algorithm that approximates a t...
read it

Deep Gaussian Processes for Regression using Approximate Expectation Propagation
Deep Gaussian processes (DGPs) are multilayer hierarchical generalisati...
read it

Rényi Divergence Variational Inference
This paper introduces the variational Rényi bound (VR) that extends trad...
read it

Training Deep Gaussian Processes using Stochastic Expectation Propagation and Probabilistic Backpropagation
Deep Gaussian processes (DGPs) are multilayer hierarchical generalisati...
read it

Stochastic Expectation Propagation for Large Scale Gaussian Process Classification
A method for large scale Gaussian process classification has been recent...
read it

Blackbox αdivergence Minimization
Blackbox alpha (BBα) is a new approximate inference method based on th...
read it

Stochastic Expectation Propagation
Expectation propagation (EP) is a deterministic approximation algorithm ...
read it