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

SelfAttention Between Datapoints: Going Beyond Individual InputOutput Pairs in Deep Learning
We challenge a common assumption underlying most supervised deep learnin...
read it

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
ResNets constrained to be biLipschitz, that is, approximately distance ...
read it

OutcomeDriven Reinforcement Learning via Variational Inference
While reinforcement learning algorithms provide automated acquisition of...
read it

PhysicallyConsistent Generative Adversarial Networks for Coastal Flood Visualization
As climate change increases the intensity of natural disasters, society ...
read it

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Counterfactual explanations (CEs) are a practical tool for demonstrating...
read it

Robustness to Pruning Predicts Generalization in Deep Neural Networks
Existing generalization measures that aim to capture a model's simplicit...
read it

Active Testing: SampleEfficient Model Evaluation
We introduce active testing: a new framework for sampleefficient model ...
read it

Quantifying Ignorance in IndividualLevel CausalEffect Estimates under Hidden Confounding
We study the problem of learning conditional average treatment effects (...
read it

PsiPhiLearning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
We study reinforcement learning (RL) with noreward demonstrations, a se...
read it

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty
We show that a single softmax neural net with minimal changes can beat t...
read it

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
We propose a new model that estimates uncertainty in a single forward pa...
read it

Domain Invariant Representation Learning with Domain Density Transformations
Domain generalization refers to the problem where we aim to train a mode...
read it

Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition
Modeling and forecasting the solar winddriven global magnetic field per...
read it

On Statistical Bias In Active Learning: How and When To Fix It
Active learning is a powerful tool when labelling data is expensive, but...
read it

On Batch Normalisation for Approximate Bayesian Inference
We study batch normalisation in the context of variational inference met...
read it

Semisupervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
The growth in the number of galaxy images is much faster than the speed ...
read it

On SignaltoNoise Ratio Issues in Variational Inference for Deep Gaussian Processes
We show that the gradient estimates used in training Deep Gaussian Proce...
read it

Interdomain Deep Gaussian Processes
Interdomain Gaussian processes (GPs) allow for high flexibility and low...
read it

A Bayesian Perspective on Training Speed and Model Selection
We take a Bayesian perspective to illustrate a connection between traini...
read it

Physicsinformed GANs for Coastal Flood Visualization
As climate change increases the intensity of natural disasters, society ...
read it

Interlocking Backpropagation: Improving depthwise modelparallelism
The number of parameters in state of the art neural networks has drastic...
read it

On the robustness of effectiveness estimation of nonpharmaceutical interventions against COVID19 transmission
There remains much uncertainty about the relative effectiveness of diffe...
read it

SliceOut: Training Transformers and CNNs faster while using less memory
We demonstrate 1040 EfficientNets, and Transformer models, with minimal...
read it

Single Shot Structured Pruning Before Training
We introduce a method to speed up training by 2x and inference by 3x in ...
read it

Identifying Causal Effect Inference Failure with UncertaintyAware Models
Recommending the best course of action for an individual is a major appl...
read it

Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Outoftrainingdistribution (OOD) scenarios are a common challenge of l...
read it

Learning Invariant Representations for Reinforcement Learning without Reconstruction
We study how representation learning can accelerate reinforcement learni...
read it

Wat zei je? Detecting OutofDistribution Translations with Variational Transformers
We detect outoftrainingdistribution sentences in Neural Machine Trans...
read it

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search
Reliable yet efficient evaluation of generalisation performance of a pro...
read it

Uncertainty Evaluation Metric for Brain Tumour Segmentation
In this paper, we develop a metric designed to assess and rank uncertain...
read it

On the Benefits of Invariance in Neural Networks
Many real world data analysis problems exhibit invariant structure, and ...
read it

Capsule Networks – A Probabilistic Perspective
'Capsule' models try to explicitly represent the poses of objects, enfor...
read it

Unpacking Information Bottlenecks: Unifying InformationTheoretic Objectives in Deep Learning
The information bottleneck (IB) principle offers both a mechanism to exp...
read it

Baryons from Mesons: A Machine Learning Perspective
Quantum chromodynamics (QCD) is the theory of the strong interaction. Th...
read it

Invariant Causal Prediction for Block MDPs
Generalization across environments is critical to the successful applica...
read it

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network
We propose a method for training a deterministic deep model that can fin...
read it

Try Depth Instead of Weight Correlations: Meanfield is a Less Restrictive Assumption for Deeper Networks
We challenge the longstanding assumption that the meanfield approximati...
read it

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Evaluation of Bayesian deep learning (BDL) methods is challenging. We of...
read it

Adversarial recovery of agent rewards from latent spaces of the limit order book
Inverse reinforcement learning has proved its ability to explain statea...
read it

AutoCalibration of Remote Sensing Solar Telescopes with Deep Learning
As a part of NASA's Heliophysics System Observatory (HSO) fleet of satel...
read it

Using UNets to Create HighFidelity Virtual Observations of the Solar Corona
Understanding and monitoring the complex and dynamic processes of the Su...
read it

SingleFrame SuperResolution of Solar Magnetograms: Investigating PhysicsBased Metrics & Losses
Breakthroughs in our understanding of physical phenomena have traditiona...
read it

Probabilistic SuperResolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
Machine learning techniques have been successfully applied to superreso...
read it

VariBAD: A Very Good Method for BayesAdaptive Deep RL via MetaLearning
Trading off exploration and exploitation in an unknown environment is ke...
read it

Machine Learning for Generalizable Prediction of Flood Susceptibility
Flooding is a destructive and dangerous hazard and climate change appear...
read it

Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder
High energy particles originating from solar activity travel along the t...
read it

Prediction of GNSS Phase Scintillations: A Machine Learning Approach
A Global Navigation Satellite System (GNSS) uses a constellation of sate...
read it

Uncertainty Quantification with Statistical Guarantees in EndtoEnd Autonomous Driving Control
Deep neural network controllers for autonomous driving have recently ben...
read it

Generalizing from a few environments in safetycritical reinforcement learning
Before deploying autonomous agents in the real world, we need to be conf...
read it
Yarin Gal
is this you? claim profile
Associate Professor of Machine Learning at the Computer Science department at University of Oxford