2.9k citations · 12k across the 144 of their papers we have counts for
37 papers · 1 filter
DARTS without a Validation Set: Optimizing the Marginal Likelihood
Miroslav Fil, Binxin Ru, Clare Lyle +1
The success of neural architecture search (NAS) has historically been limited by excessive compute requirements. While modern weight-sharing NAS methods such as DARTS are able to f…
QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
Raghav Mehta, Angelos Filos, Ujjwal Baid +89
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges.…
Investigating an Alternative for Estimation from a Nonprobability Sample: Matching plus Calibration
Zhan Liu, Richard Valliant
Matching a nonprobability sample to a probability sample is one strategy both for selecting the nonprobability units and for weighting them. This approach has been employed in the…
DeDUCE: Generating Counterfactual Explanations Efficiently
Benedikt Höltgen, Lisa Schut, Jan M. Brauner +1
When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms gener…
Contrastive Representation Learning with Trainable Augmentation Channel
Masanori Koyama, Kentaro Minami, Takeru Miyato +1
In contrastive representation learning, data representation is trained so that it can classify the image instances even when the images are altered by augmentations. However, depen…
Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation
Muhammed Razzak, Gonzalo Mateo-Garcia, Luis Gómez-Chova +2
High resolution remote sensing imagery is used in broad range of tasks, including detection and classification of objects. High-resolution imagery is however expensive, while lower…
Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific
Andrew Jesson, Peter Manshausen, Alyson Douglas +3
Aerosol-cloud interactions include a myriad of effects that all begin when aerosol enters a cloud and acts as cloud condensation nuclei (CCN). An increase in CCN results in a decre…
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
Andrew Jesson, Panagiotis Tigas, Joost van Amersfoort +3
Estimating personalized treatment effects from high-dimensional observational data is essential in situations where experimental designs are infeasible, unethical, or expensive. Ex…
Deep Deterministic Uncertainty for Semantic Segmentation
Jishnu Mukhoti, Joost van Amersfoort, Philip H. S. Torr +1
We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangli…
GeneDisco: A Benchmark for Experimental Design in Drug Discovery
Arash Mehrjou, Ashkan Soleymani, Andrew Jesson +4
In vitro cellular experimentation with genetic interventions, using for example CRISPR technologies, is an essential step in early-stage drug discovery and target validation that s…
Quantifying Uncertainty for Machine Learning Based Diagnostic
Owen Convery, Lewis Smith, Yarin Gal +1
Virtual Diagnostic (VD) is a deep learning tool that can be used to predict a diagnostic output. VDs are especially useful in systems where measuring the output is invasive, limite…
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Andrey Malinin, Neil Band, Ganshin +17
There has been significant research done on developing methods for improving robustness to distributional shift and uncertainty estimation. In contrast, only limited work has exami…
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)
Sören Mindermann, Muhammed Razzak, Winnie Xu +7
We introduce Goldilocks Selection, a technique for faster model training which selects a sequence of training points that are "just right". We propose an information-theoretic acqu…
Improving black-box optimization in VAE latent space using decoder uncertainty
Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal
Optimization in the latent space of variational autoencoders is a promising approach to generate high-dimensional discrete objects that maximize an expensive black-box property (e.…
Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Lewis Smith, Joost van Amersfoort, Haiwen Huang +2
ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quan…
A Practical & Unified Notation for Information-Theoretic Quantities in ML
Andreas Kirsch, Yarin Gal
A practical notation can convey valuable intuitions and concisely express new ideas. Information theory is of importance to machine learning, but the notation for information-theor…
Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning
Andreas Kirsch, Sebastian Farquhar, Parmida Atighehchian +3
We examine a simple stochastic strategy for adapting well-known single-point acquisition functions to allow batch active learning. Unlike acquiring the top-K points from the pool s…
Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers
Andreas Kirsch, Tom Rainforth, Yarin Gal
Expanding on MacKay (1992), we argue that conventional model-based methods for active learning - like BALD - have a fundamental shortfall: they fail to directly account for the tes…
KL Guided Domain Adaptation
A. Tuan Nguyen, Toan Tran, Yarin Gal +2
Domain adaptation is an important problem and often needed for real-world applications. In this problem, instead of i.i.d. training and testing datapoints, we assume that the sourc…
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Zachary Nado, Neil Band, Mark Collier +23
High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ab…
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Jannik Kossen, Neil Band, Clare Lyle +3
We challenge a common assumption underlying most supervised deep learning: that a model makes a prediction depending only on its parameters and the features of a single input. To t…
Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators
Owen Convery, Lewis Smith, Yarin Gal +1
Virtual Diagnostic (VD) is a computational tool based on deep learning that can be used to predict a diagnostic output. VDs are especially useful in systems where measuring the out…
Outcome-Driven Reinforcement Learning via Variational Inference
Tim G. J. Rudner, Vitchyr H. Pong, Rowan McAllister +2
While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manu…
Generating Physically-Consistent Satellite Imagery for Climate Visualizations
Björn Lütjens, Brandon Leshchinskiy, Océane Boulais +11
Deep generative vision models are now able to synthesize realistic-looking satellite imagery. But, the possibility of hallucinations prevents their adoption for risk-sensitive appl…