
BEDSBench: Behavior of EHRmodels under Distributional Shift–A Benchmark
Machine learning has recently demonstrated impressive progress in predic...
read it

Taskagnostic Continual Learning with Hybrid Probabilistic Models
Learning new tasks continuously without forgetting on a constantly chang...
read it

A Simple Fix to Mahalanobis Distance for Improving NearOOD Detection
Mahalanobis distance (MD) is a simple and popular postprocessing method...
read it

Predicting Unreliable Predictions by Shattering a Neural Network
Piecewise linear neural networks can be split into subfunctions, each wi...
read it

Uncertainty Baselines: Benchmarks for Uncertainty Robustness in Deep Learning
Highquality estimates of uncertainty and robustness are crucial for num...
read it

Exploring the Limits of OutofDistribution Detection
Near outofdistribution detection (OOD) is a major challenge for deep n...
read it

Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the LongTail of Unseen Conditions
We develop and rigorously evaluate a deep learning based system that can...
read it

Combining Ensembles and Data Augmentation can Harm your Calibration
Ensemble methods which average over multiple neural network predictions ...
read it

Training independent subnetworks for robust prediction
Recent approaches to efficiently ensemble neural networks have shown tha...
read it

Bayesian Deep Ensembles via the Neural Tangent Kernel
We explore the link between deep ensembles and Gaussian processes (GPs) ...
read it

Revisiting OnevsAll Classifiers for Predictive Uncertainty and OutofDistribution Detection in Neural Networks
Accurate estimation of predictive uncertainty in modern neural networks ...
read it

Evaluating PredictionTime Batch Normalization for Robustness under Covariate Shift
Covariate shift has been shown to sharply degrade both predictive accura...
read it

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
Bayesian neural networks (BNN) and deep ensembles are principled approac...
read it

Density of States Estimation for OutofDistribution Detection
Perhaps surprisingly, recent studies have shown probabilistic model like...
read it

Efficient and Scalable Bayesian Neural Nets with Rank1 Factors
Bayesian neural networks (BNNs) demonstrate promising success in improvi...
read it

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Modern deep neural networks can achieve high accuracy when the training ...
read it

Normalizing Flows for Probabilistic Modeling and Inference
Normalizing flows provide a general mechanism for defining expressive pr...
read it

Deep Ensembles: A Loss Landscape Perspective
Deep ensembles have been empirically shown to be a promising approach fo...
read 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...
read it

Likelihood Ratios for OutofDistribution Detection
Discriminative neural networks offer little or no performance guarantees...
read it

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Modern machine learning methods including deep learning have achieved gr...
read it

Hybrid Models with Deep and Invertible Features
We propose a neural hybrid model consisting of a linear model defined on...
read it

Adapting Auxiliary Losses Using Gradient Similarity
One approach to deal with the statistical inefficiency of neural network...
read 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...
read it

Learning from Delayed Outcomes with Intermediate Observations
Optimizing for long term value is desirable in many practical applicatio...
read it

Distribution Matching in Variational Inference
The difficulties in matching the latent posterior to the prior, balancin...
read it

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Generative adversarial networks (GANs) are a family of generative models...
read it

Variational Approaches for AutoEncoding Generative Adversarial Networks
Autoencoding generative adversarial networks (GANs) combine the standar...
read it

The Cramer Distance as a Solution to Biased Wasserstein Gradients
The Wasserstein probability metric has received much attention from the ...
read it

Learning in Implicit Generative Models
Generative adversarial networks (GANs) provide an algorithmic framework ...
read it

The Mondrian Kernel
We introduce the Mondrian kernel, a fast random feature approximation to...
read it

Distributed Bayesian Learning with Stochastic Naturalgradient Expectation Propagation and the Posterior Server
This paper makes two contributions to Bayesian machine learning algorith...
read it

Approximate Inference with the Variational Holder Bound
We introduce the Variational Holder (VH) bound as an alternative to Vari...
read it

Mondrian Forests for LargeScale Regression when Uncertainty Matters
Many realworld regression problems demand a measure of the uncertainty ...
read it

KernelBased JustInTime Learning for Passing Expectation Propagation Messages
We propose an efficient nonparametric strategy for learning a message op...
read it

Particle Gibbs for Bayesian Additive Regression Trees
Additive regression trees are flexible nonparametric models and popular...
read it

Inferring ground truth from multiannotator ordinal data: a probabilistic approach
A popular approach for large scale data annotation tasks is crowdsourcin...
read it

Topdown particle filtering for Bayesian decision trees
Decision tree learning is a popular approach for classification and regr...
read it