Yarin Gal

Bio: Yarin Gal is an academic researcher from University of Oxford. The author has contributed to research in topics: Uncertainty quantification & Artificial neural network. The author has an hindex of 4, co-authored 26 publications receiving 70 citations.

Technology Readiness Levels for Machine Learning Systems.

Abstract: The development and deployment of machine learning 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 AI/ML (from research through product), we propose a proven systems engineering approach for machine learning development and deployment Our Technology Readiness Levels for ML (TRL4ML) framework defines a principled process to ensure robust systems while being streamlined for ML research and product, including key distinctions from traditional software engineering Even more, TRL4ML defines a common language for people across the organization to work collaboratively on ML technologies

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

Abstract: We show that a single softmax neural net with minimal changes can beat the uncertainty predictions of Deep Ensembles and other more complex single-forward-pass uncertainty approaches. Softmax neural nets cannot capture epistemic uncertainty reliably because for OoD points they extrapolate arbitrarily and suffer from feature collapse. This results in arbitrary softmax entropies for OoD points which can have high entropy, low, or anything in between. We study why, and show that with the right inductive biases, softmax neural nets trained with maximum likelihood reliably capture epistemic uncertainty through the feature-space density. This density is obtained using Gaussian Discriminant Analysis, but it cannot disentangle uncertainties. We show that it is necessary to combine this density with the softmax entropy to disentangle aleatoric and epistemic uncertainty -- crucial e.g. for active learning. We examine the quality of epistemic uncertainty on active learning and OoD detection, where we obtain SOTA ~0.98 AUROC on CIFAR-10 vs SVHN.

On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty

Abstract: Gaussian processes are often considered a gold standard in uncertainty estimation with low dimensional data, but they have difficulty scaling to high dimensional inputs. Deep Kernel Learning (DKL) was introduced as a solution to this problem: a deep feature extractor is used to transform the inputs over which a Gaussian process' kernel is defined. However, DKL has been shown to provide unreliable uncertainty estimates in practice. We study why, and show that for certain feature extractors, "far-away" data points are mapped to the same features as those of training-set points. With this insight we propose to constrain DKL's feature extractor to approximately preserve distances through a bi-Lipschitz constraint, resulting in a feature space favorable to DKL. We obtain a model, DUE, which demonstrates uncertainty quality outperforming previous DKL and single forward pass uncertainty methods, while maintaining the speed and accuracy of softmax neural networks.

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression.

Abstract: We propose a new model that estimates uncertainty in a single forward pass and works on both classification and regression problems. Our approach combines a bi-Lipschitz feature extractor with an inducing point approximate Gaussian process, offering robust and principled uncertainty estimation. This can be seen as a refinement of Deep Kernel Learning (DKL), with our changes allowing DKL to match softmax neural networks accuracy. Our method overcomes the limitations of previous work addressing deterministic uncertainty quantification, such as the dependence of uncertainty on ad hoc hyper-parameters. Our method matches SotA accuracy, 96.2% on CIFAR-10, while maintaining the speed of softmax models, and provides uncertainty estimates that outperform previous single forward pass uncertainty models. Finally, we demonstrate our method on a recently introduced benchmark for uncertainty in regression: treatment deferral in causal models for personalized medicine.

Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators

Abstract: 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 output is invasive, limited, costly or runs the risk of altering the output. Given a prediction, it is necessary to relay how reliable that prediction is, i.e. quantify the uncertainty of the 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 National Lab. 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.

Inferring the effectiveness of government interventions against COVID-19.

Abstract: Governments are attempting to control the COVID-19 pandemic with nonpharmaceutical interventions (NPIs). However, the effectiveness of different NPIs at reducing transmission is poorly understood. We gathered chronological data on the implementation of NPIs for several European, and other, countries between January and the end of May 2020. We estimate the effectiveness of NPIs, ranging from limiting gathering sizes, business closures, and closure of educational institutions to stay-at-home orders. To do so, we used a Bayesian hierarchical model that links NPI implementation dates to national case and death counts and supported the results with extensive empirical validation. Closing all educational institutions, limiting gatherings to 10 people or less, and closing face-to-face businesses each reduced transmission considerably. The additional effect of stay-at-home orders was comparatively small.

Challenges in Deploying Machine Learning: a Survey of Case Studies

Abstract: In recent years, machine learning has received increased interest both as an academic research field and as a solution for real-world business problems. However, the deployment of machine learning models in production systems can present a number of issues and concerns. This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries and applications and extracts practical considerations corresponding to stages of the machine learning deployment workflow. Our survey shows that practitioners face challenges at each stage of the deployment. The goal of this paper is to layout a research agenda to explore approaches addressing these challenges.