arXiv subjects

Yarin Gal

Publications and source records attributed to Yarin Gal.

At least 127 records · Page 7Linked to original sources

arXiv2022

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

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 this end, we introduce a general-purpose deep learning architecture that takes as input the entire dataset instead of processing one datapoint at a time. Our approach uses self-attention to reason about relationships between datapoints explicitly, which can be seen as realizing non-parametric models using parametric attention mechanisms. However, unlike conventional non-parametric models, we let the model learn end-to-end from the data how to make use of other datapoints for prediction. Empirically, our models solve cross-datapoint lookup and complex reasoning tasks unsolvable by traditional deep learning models. We show highly competitive results on tabular data, early results on CIFAR-10, and give insight into how the model makes use of the interactions between points.

cs.LG↗

arXiv2022

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

Estimating personalized treatment effects from high-dimensional observational data is essential in situations where experimental designs are infeasible, unethical, or expensive. Existing approaches rely on fitting deep models on outcomes observed for treated and control populations. However, when measuring individual outcomes is costly, as is the case of a tumor biopsy, a sample-efficient strategy for acquiring each result is required. Deep Bayesian active learning provides a framework for efficient data acquisition by selecting points with high uncertainty. However, existing methods bias training data acquisition towards regions of non-overlapping support between the treated and control populations. These are not sample-efficient because the treatment effect is not identifiable in such regions. We introduce causal, Bayesian acquisition functions grounded in information theory that bias data acquisition towards regions with overlapping support to maximize sample efficiency for learning personalized treatment effects. We demonstrate the performance of the proposed acquisition strategies on synthetic and semi-synthetic datasets IHDP and CMNIST and their extensions, which aim to simulate common dataset biases and pathologies.

cs.LG↗

arXiv2022

Deep Deterministic Uncertainty: A Simple Baseline

Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass uncertainty approaches, DUQ and SNGP, and examine whether they mainly rely on a well-regularized feature space. Crucially, without using their more complex methods for estimating uncertainty, a single softmax neural net with such a feature-space, achieved via residual connections and spectral normalization, *outperforms* DUQ and SNGP's epistemic uncertainty predictions using simple Gaussian Discriminant Analysis *post-training* as a separate feature-space density estimator -- without fine-tuning on OoD data, feature ensembling, or input pre-procressing. This conceptually simple *Deep Deterministic Uncertainty (DDU)* baseline can also be used to disentangle aleatoric and epistemic uncertainty and performs as well as Deep Ensembles, the state-of-the art for uncertainty prediction, on several OoD benchmarks (CIFAR-10/100 vs SVHN/Tiny-ImageNet, ImageNet vs ImageNet-O) as well as in active learning settings across different model architectures, yet is *computationally cheaper*.

cs.LG↗

arXiv2022

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

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 ability to compare techniques for improving these estimates is therefore very important for research and practice alike. Yet, competitive comparisons of methods are often lacking due to a range of reasons, including: compute availability for extensive tuning, incorporation of sufficiently many baselines, and concrete documentation for reproducibility. In this paper we introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks. As of this writing, the collection spans 19 methods across 9 tasks, each with at least 5 metrics. Each baseline is a self-contained experiment pipeline with easily reusable and extendable components. Our goal is to provide immediate starting points for experimentation with new methods or applications. Additionally we provide model checkpoints, experiment outputs as Python notebooks, and leaderboards for comparing results. Code available at https://github.com/google/uncertainty-baselines.

cs.LG↗

arXiv2022

Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies

We present Galaxy Zoo DECaLS: detailed visual morphological classifications for Dark Energy Camera Legacy Survey images of galaxies within the SDSS DR8 footprint. Deeper DECaLS images (r=23.6 vs. r=22.2 from SDSS) reveal spiral arms, weak bars, and tidal features not previously visible in SDSS imaging. To best exploit the greater depth of DECaLS images, volunteers select from a new set of answers designed to improve our sensitivity to mergers and bars. Galaxy Zoo volunteers provide 7.5 million individual classifications over 314,000 galaxies. 140,000 galaxies receive at least 30 classifications, sufficient to accurately measure detailed morphology like bars, and the remainder receive approximately 5. All classifications are used to train an ensemble of Bayesian convolutional neural networks (a state-of-the-art deep learning method) to predict posteriors for the detailed morphology of all 314,000 galaxies. When measured against confident volunteer classifications, the networks are approximately 99% accurate on every question. Morphology is a fundamental feature of every galaxy; our human and machine classifications are an accurate and detailed resource for understanding how galaxies evolve.

astro-ph.GA↗

arXiv2021

DARTS without a Validation Set: Optimizing the Marginal Likelihood

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 finish the search in single-digit GPU days, extracting the final best architecture from the shared weights is notoriously unreliable. Training-Speed-Estimate (TSE), a recently developed generalization estimator with a Bayesian marginal likelihood interpretation, has previously been used in place of the validation loss for gradient-based optimization in DARTS. This prevents the DARTS skip connection collapse, which significantly improves performance on NASBench-201 and the original DARTS search space. We extend those results by applying various DARTS diagnostics and show several unusual behaviors arising from not using a validation set. Furthermore, our experiments yield concrete examples of the depth gap and topology selection in DARTS having a strongly negative impact on the search performance despite generally receiving limited attention in the literature compared to the operations selection.

cs.LG↗

arXiv2021

A Practical & Unified Notation for Information-Theoretic Quantities in ML

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-theoretic quantities is sometimes opaque. We propose a practical and unified notation and extend it to include information-theoretic quantities between observed outcomes (events) and random variables. This includes the point-wise mutual information known in NLP and mixed quantities such as specific surprise and specific information in the cognitive sciences and information gain in Bayesian optimal experimental design. We apply our notation to prove a version of Stirling's approximation for binomial coefficients mentioned by MacKa (2003) using new intuitions. We also concisely rederive the evidence lower bound for variational auto-encoders and variational inference in approximate Bayesian neural networks. Furthermore, we apply the notation to a popular information-theoretic acquisition function in Bayesian active learning which selects the most informative (unlabelled) samples to be labelled by an expert and extend this acquisition function to the core-set problem with the goal of selecting the most informative samples given the labels.

cs.LG↗

arXiv2021

Decomposing Representations for Deterministic Uncertainty Estimation

Uncertainty estimation is a key component in any deployed machine learning system. One way to evaluate uncertainty estimation is using "out-of-distribution" (OoD) detection, that is, distinguishing between the training data distribution and an unseen different data distribution using uncertainty. In this work, we show that current feature density based uncertainty estimators cannot perform well consistently across different OoD detection settings. To solve this, we propose to decompose the learned representations and integrate the uncertainties estimated on them separately. Through experiments, we demonstrate that we can greatly improve the performance and the interpretability of the uncertainty estimation.

cs.LG↗

arXiv2021

DeDUCE: Generating Counterfactual Explanations Efficiently

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 generating counterfactual explanations. However, there is no easily scalable method to generate such counterfactuals. We develop a new algorithm providing counterfactual explanations for large image classifiers trained with spectral normalisation at low computational cost. We empirically compare this algorithm against baselines from the literature; our novel algorithm consistently finds counterfactuals that are much closer to the original inputs. At the same time, the realism of these counterfactuals is comparable to the baselines. The code for all experiments is available at https://github.com/benedikthoeltgen/DeDUCE.

cs.CV↗

arXiv2021

Technology Readiness Levels for Machine Learning Systems

The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. The lack of diligence can lead to technical debt, scope creep and misaligned objectives, model misuse and failures, and expensive consequences. Engineering systems, on the other hand, follow well-defined processes and testing standards to streamline development for high-quality, reliable results. The extreme is spacecraft systems, where mission critical measures and robustness are ingrained in the development process. Drawing on experience in both spacecraft engineering and ML (from research through product across domain areas), we have developed a proven systems engineering approach for machine learning development and deployment. Our "Machine Learning Technology Readiness Levels" (MLTRL) framework defines a principled process to ensure robust, reliable, and responsible systems while being streamlined for ML workflows, including key distinctions from traditional software engineering. Even more, MLTRL defines a lingua franca for people across teams and organizations to work collaboratively on artificial intelligence and machine learning technologies. Here we describe the framework and elucidate it with several real world use-cases of developing ML methods from basic research through productization and deployment, in areas such as medical diagnostics, consumer computer vision, satellite imagery, and particle physics.

cs.LG↗

arXiv2021

Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers

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 test-time distribution of the input variables. This can lead to pathologies in the acquisition strategy, as what is maximally informative for model parameters may not be maximally informative for prediction: for example, when the data in the pool set is more dispersed than that of the final prediction task, or when the distribution of pool and test samples differs. To correct this, we revisit an acquisition strategy that is based on maximizing the expected information gained about possible future predictions, referring to this as the Expected Predictive Information Gain (EPIG). As EPIG does not scale well for batch acquisition, we further examine an alternative strategy, a hybrid between BALD and EPIG, which we call the Joint Expected Predictive Information Gain (JEPIG). We consider using both for active learning with Bayesian neural networks on a variety of datasets, examining the behavior under distribution shift in the pool set.

cs.LG↗

arXiv2021

Contrastive Representation Learning with Trainable Augmentation Channel

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, depending on the datasets, some augmentations can damage the information of the images beyond recognition, and such augmentations can result in collapsed representations. We present a partial solution to this problem by formalizing a stochastic encoding process in which there exist a tug-of-war between the data corruption introduced by the augmentations and the information preserved by the encoder. We show that, with the infoMax objective based on this framework, we can learn a data-dependent distribution of augmentations to avoid the collapse of the representation.

stat.ML↗

arXiv2021

Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation

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 resolution imagery is often freely available and can be used by the public for range of social good applications. To that end, we curate a multi-spectral multi-image super-resolution dataset, using PlanetScope imagery from the SpaceNet 7 challenge as the high resolution reference and multiple Sentinel-2 revisits of the same imagery as the low-resolution imagery. We present the first results of applying multi-image super-resolution (MISR) to multi-spectral remote sensing imagery. We, additionally, introduce a radiometric consistency module into MISR model the to preserve the high radiometric resolution of the Sentinel-2 sensor. We show that MISR is superior to single-image super-resolution and other baselines on a range of image fidelity metrics. Furthermore, we conduct the first assessment of the utility of multi-image super-resolution on building delineation, showing that utilising multiple images results in better performance in these downstream tasks.

eess.IV↗

arXiv2021

Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific

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 decrease in the mean cloud droplet size (r$_{e}$). The smaller droplet size leads to brighter, more expansive, and longer lasting clouds that reflect more incoming sunlight, thus cooling the earth. Globally, aerosol-cloud interactions cool the Earth, however the strength of the effect is heterogeneous over different meteorological regimes. Understanding how aerosol-cloud interactions evolve as a function of the local environment can help us better understand sources of error in our Earth system models, which currently fail to reproduce the observed relationships. In this work we use recent non-linear, causal machine learning methods to study the heterogeneous effects of aerosols on cloud droplet radius.

physics.ao-ph↗

arXiv2021

Deep Deterministic Uncertainty for Semantic Segmentation

We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangling epistemic and aleatoric uncertainty in a single forward pass through the model. We study the similarity of feature representations of pixels at different locations for the same class and conclude that it is feasible to apply DDU location independently, which leads to a significant reduction in memory consumption compared to pixel dependent DDU. Using the DeepLab-v3+ architecture on Pascal VOC 2012, we show that DDU improves upon MC Dropout and Deep Ensembles while being significantly faster to compute.

cs.CV↗

arXiv2021

GeneDisco: A Benchmark for Experimental Design in Drug Discovery

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 serves to assess initial hypotheses about causal associations between biological mechanisms and disease pathologies. With billions of potential hypotheses to test, the experimental design space for in vitro genetic experiments is extremely vast, and the available experimental capacity - even at the largest research institutions in the world - pales in relation to the size of this biological hypothesis space. Machine learning methods, such as active and reinforcement learning, could aid in optimally exploring the vast biological space by integrating prior knowledge from various information sources as well as extrapolating to yet unexplored areas of the experimental design space based on available data. However, there exist no standardised benchmarks and data sets for this challenging task and little research has been conducted in this area to date. Here, we introduce GeneDisco, a benchmark suite for evaluating active learning algorithms for experimental design in drug discovery. GeneDisco contains a curated set of multiple publicly available experimental data sets as well as open-source implementations of state-of-the-art active learning policies for experimental design and exploration.

cs.LG↗

arXiv2021

Quantifying Uncertainty for Machine Learning Based Diagnostic

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, limited, costly or runs the risk of damaging the output. Given a prediction, it is necessary to relay how reliable that prediction is. This is known as 'uncertainty quantification' of a prediction. In this paper, we use ensemble methods and quantile regression neural networks to explore different ways of creating and analyzing prediction's uncertainty on experimental data from the Linac Coherent Light Source at SLAC. We aim to accurately and confidently predict the current profile or longitudinal phase space images of the electron beam. The ability to make informed decisions under uncertainty is crucial for reliable deployment of deep learning tools on safety-critical systems as particle accelerators.

physics.acc-ph↗

arXiv2021

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

We show that the gradient estimates used in training Deep Gaussian Processes (DGPs) with importance-weighted variational inference are susceptible to signal-to-noise ratio (SNR) issues. Specifically, we show both theoretically and via an extensive empirical evaluation that the SNR of the gradient estimates for the latent variable's variational parameters decreases as the number of importance samples increases. As a result, these gradient estimates degrade to pure noise if the number of importance samples is too large. To address this pathology, we show how doubly reparameterized gradient estimators, originally proposed for training variational autoencoders, can be adapted to the DGP setting and that the resultant estimators completely remedy the SNR issue, thereby providing more reliable training. Finally, we demonstrate that our fix can lead to consistent improvements in the predictive performance of DGP models.

stat.ML↗