Jump to Content
Jasper Snoek

Jasper Snoek

I completed my PhD in machine learning at the University of Toronto in 2013. Subsequently, I held postdoctoral fellowships at the University of Toronto, under Geoffrey Hinton and Ruslan Salakhutdinov, and at the Harvard Center for Research on Computation and Society, under Ryan Adams. While at Harvard I co-founded the machine learning startup Whetlab, which was acquired by Twitter in 2015. Currently, I am a research scientist at Google Brain in Cambridge, MA.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, desc
  • Year
  • Year, desc
    Preview abstract Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the issues with the underlying member networks. In this work, we study principled approaches to improve uncertainty property of a single network, based on a single, deterministic representation. By formalizing the uncertainty quantification as a minimax learning problem, we first identify distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs with two simple changes: (1) applying spectral normalization to hidden weights to enforce bi-Lipschitz smoothness in representations and (2) replacing the last output layer with a Gaussian process layer. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection. Furthermore, SNGP provides complementary benefits to popular techniques such as deep ensembles and data augmentation, making it a simple and scalable building block for probabilistic deep learning. Code is open-sourced at https://github.com/google/uncertainty-baselines. View details
    Plex: Towards Reliability using Pretrained Large Model Extensions
    Du Phan
    Mark Patrick Collier
    Zi Wang
    Zelda Mariet
    Clara Huiyi Hu
    Neil Band
    Tim G. J. Rudner
    Joost van Amersfoort
    Andreas Christian Kirsch
    Rodolphe Jenatton
    Honglin Yuan
    Kelly Buchanan
    Yarin Gal
    ICML 2022 Pre-training Workshop (2022)
    Preview abstract A recent trend in artificial intelligence (AI) is the use of pretrained models for language and vision tasks, which has achieved extraordinary performance but also puzzling failures. Examining tasks that probe the model’s abilities in diverse ways is therefore critical to the field. In this paper, we explore the \emph{reliability} of models, where we define a reliable model as one that not only achieves strong predictive performance but also performs well consistently over many decision-making tasks such as uncertainty (e.g., selective prediction, open set recognition), robust generalization (e.g., accuracy and scoring rules such as log-likelihood on in- and out-of-distribution datasets), and adaptation (e.g., active learning, few-shot learning). We devise 11 types of tasks over 36 datasets in order to evaluate different aspects of reliability on both vision and language domains. To improve reliability, we developed ViT-Plex and T5-Plex, \emph{p}retrained \emph{l}arge-model \emph{ex}tensions (henceforth abbreviated as \emph{plex}) for vision and language modalities. Plex greatly improves the state-of-the-art across tasks, and as a pretrained model Plex unifies the traditional protocol of designing and tuning one model for each reliability task. We demonstrate scaling effects over model sizes and pretraining dataset sizes up to 4 billion examples. We also demonstrate Plex’s capabilities on new tasks including zero-shot open set recognition, few-shot uncertainty, and uncertainty in conversational language understanding. View details
    Combining Ensembles and Data Augmentation Can Harm Your Calibration
    Yeming Wen
    Ghassen Jerfel
    Rafael Rios Müller
    International Conference on Learning Representations (2021)
    Preview abstract Ensemble methods which average over multiple neural network predictions are a simple approach to improve a model’s calibration and robustness. Similarly, data augmentation techniques, which encode prior information in the form of invariant feature transformations, are effective for improving calibration and robustness. In this paper, we show a surprising pathology: combining ensembles and data augmentation can harm model calibration. This leads to a trade-off in practice, whereby improved accuracy by combining the two techniques comes at the expense of calibration. On the other hand, selecting only one of the techniques ensures good uncertainty estimates at the expense of accuracy. We investigate this pathology and identify a compounding under-confidence among methods which marginalize over sets of weights and data augmentation techniques which soften labels. Finally, we propose a simple correction, achieving the best of both worlds with significant accuracy and calibration gains over using only ensembles or data augmentation individually. Applying the correction produces new state-of-the art in uncertainty calibration and robustness across CIFAR-10, CIFAR-100, and ImageNet. View details
    Training independent subnetworks for robust prediction
    Marton Havasi
    Rodolphe Jenatton
    Stanislav Fort
    International Conference on Learning Representations (2021)
    Preview abstract Recent approaches to efficiently ensemble neural networks have shown that strong robustness and uncertainty performance can be achieved with a negligible gain in parameters over the original network. However, these methods still require multiple forward passes for prediction, leading to a significant runtime cost. In this work, we show a surprising result: the benefits of using multiple predictions can be achieved 'for free' under a single model's forward pass. In particular, we show that, using a multi-input multi-output (MIMO) configuration, one can utilize a single model's capacity to train multiple subnetworks that independently learn the task at hand. By ensembling the predictions made by the subnetworks, we improve model robustness without increasing compute. We observe a significant improvement in negative log-likelihood, accuracy, and calibration error on CIFAR10, CIFAR100, ImageNet, and their out-of-distribution variants compared to previous methods. View details
    Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width Limit
    Jeffrey Pennington
    International Conference on Learning Representations, 2021, International Conference on Learning Representations, 2021, 27 pages
    Preview abstract Modern deep learning models have achieved great success in predictive accuracy for many data modalities. However, their application to many real-world tasks is restricted by poor uncertainty estimates, such as overconfidence on out-of-distribution (OOD) data and ungraceful failing under distributional shift. Previous benchmarks have found that ensembles of neural networks (NNs) are typically the best calibrated models on OOD data. Inspired by this, we leverage recent theoretical advances that characterize the function-space prior of an infinitely-wide NN as a Gaussian process, termed the neural network Gaussian process (NNGP). We use the NNGP with a softmax link function to build a probabilistic model for multi-class classification and marginalize over the latent Gaussian outputs to sample from the posterior. This gives us a better understanding of the implicit prior NNs place on function space and allows a direct comparison of the calibration of the NNGP and its finite-width analogue. We also examine the calibration of previous approaches to classification with the NNGP, which treat classification problems as regression to the one-hot labels. In this case the Bayesian posterior is exact, and we compare several heuristics to generate a categorical distribution over classes. We find these methods are well calibrated under distributional shift. Finally, we consider an infinite-width final layer in conjunction with a pre-trained embedding. This replicates the important practical use case of transfer learning and allows scaling to significantly larger datasets. As well as achieving competitive predictive accuracy, this approach is better calibrated than its finite width analogue. View details
    Cold Posteriors and Aleatoric Uncertainty
    ICML workshop on Uncertainty and Robustness in Deep Learning (2020)
    Preview abstract Recent work has observed that one can outperform exact inference in Bayesian neural networks by tuning the "temperature" of the posterior on a validation set (the "cold posterior" effect). To help interpret this phenomenon, we argue that commonly used priors in Bayesian neural networks can significantly overestimate the aleatoric uncertainty in the labels on many classification datasets. This problem is particularly pronounced in academic benchmarks like MNIST or CIFAR, for which the quality of the labels is high. For the special case of Gaussian process regression, any positive temperature corresponds to a valid posterior under a modified prior, and tuning this temperature is directly analogous to empirical Bayes. On classification tasks, there is no direct equivalence between modifying the prior and tuning the temperature, however reducing the temperature can lead to models which better reflect our belief that one gains little information by relabeling existing examples in the training set. Therefore although cold posteriors do not always correspond to an exact inference procedure, we believe they may often better reflect our true prior beliefs. View details
    Preview abstract Speech synthesis is an important practical generative modeling problem that has seen great progress over the last few years, with likelihood-based autoregressive neural models now outperforming traditional concatenative systems. A downside of such autoregressive models is that they require executing tens of thousands of sequential operations per second of generated audio, making them ill-suited for deployment on specialized deep learning hardware. Here, we propose a new learning method that allows us to train highly parallel models of speech, without requiring access to an analytical likelihood function. Our approach is based on a generalized energy distance between the distributions of the generated and real audio. This spectral energy distance is a proper scoring rule with respect to the distribution over magnitude-spectrograms of the generated waveform audio and offers statistical consistency guarantees. The distance can be calculated from minibatches without bias, and does not involve adversarial learning, yielding a stable and consistent method for training implicit generative models. Empirically, we achieve state-of-the-art generation quality among implicit generative models, as judged by the recently proposed cFDSD metric. When combining our method with adversarial techniques, we also improve upon the recently proposed GAN-TTS model in terms of Mean Opinion Score as judged by trained human evaluators. View details
    Preview abstract Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern neural networks. However, they generally struggle with underfitting at scale and parameter efficiency. On the other hand, deep ensembles have emerged as an alternative for uncertainty quantification that, while outperforming BNNs on certain problems, also suffers from efficiency issues. It remains unclear how to combine the strengths of these two approaches and remediate their common issues. To tackle this challenge, we propose a rank-1 parameterization of BNNs, where each weight matrix involves only a distribution on a rank-1 subspace. We also revisit the use of mixture approximate posteriors to capture multiple modes where unlike typical mixtures, this approach admits a significantly smaller memory increase (e.g., only a 0.4% increase for a ResNet-50 mixture of size 10). We perform a systematic empirical study on the choices of prior, variational posterior, and methods to improve training. For ResNet-50 on ImageNet and Wide ResNet 28-10 on CIFAR-10/100, rank-1 BNNs outperform baselines across log-likelihood, accuracy, and calibration on the test set and out-of-distribution variants. View details
    Preview abstract Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution inputs. The most promising approaches have been predominantly focused on improving model uncertainty (e.g. deep ensembles and Bayesian neural networks) and post-processing techniques for out-of-distribution detection (e.g. ODIN and Mahalanobis distance). However, there has been relatively little investigation into how the parametrization of the probabilities in discriminative classifiers affects the uncertainty estimates, and the dominant method, softmax cross-entropy, results in misleadingly high confidences on out-of-distribution data and under covariate shift. We investigate alternative ways of formulating probabilities using (1) a one-vs-all formulation to capture the notion of “none of the above”, and (2) a distance-based logit representation to encode uncertainty as a function of distance to the training manifold. We show that one-vs-all formulations can match the predictive performance of softmax without incurring any additional training or test-time complexity, and improve calibration on image classification tasks. View details
    Hyperparameter Ensembles for Robustness and Uncertainty Quantification
    Florian Wenzel
    Rodolphe Jenatton
    Neural Information Processing Systems (NeurIPS) (2020)
    Preview abstract Ensembles over neural network weights trained from different random initialization, known as deep ensembles, achieve state-of-the-art accuracy and calibration. The recently introduced batch ensembles provide a drop-in replacement that is more parameter efficient. In this paper, we design ensembles not only over weights, but over hyperparameters to improve the state of the art in both settings. For best performance independent of budget, we propose hyper-deep ensembles, a simple procedure that involves a random search over different hyperparameters, themselves stratified across multiple random initializations. Its strong performance highlights the benefit of combining models with both weight and hyperparameter diversity. We further propose a parameter efficient version, hyper-batch ensembles, which builds on the layer structure of batch ensembles and self-tuning networks. The computational and memory costs of our method are notably lower than typical ensembles. On image classification tasks, with MLP, LeNet, ResNet 20 and Wide ResNet 28-10 architectures, we improve upon both deep and batch ensembles. View details
    Preview abstract Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}. Quantifying uncertainty is especially critical in real-world settings, which often involve distributions that are skewed from the training distribution due to a variety of factors including sample bias and non-stationarity. In such settings, well calibrated uncertainty estimates convey information about when a model's output should (or should not) be trusted. Many probabilistic deep learning methods, including Bayesian-and non-Bayesian methods, have been proposed in the literature for quantifying predictive uncertainty, but to our knowledge there has not previously been a rigorous large-scale empirical comparison of these methods under conditions of distributional skew. We present a large-scale benchmark of existing state-of-the-art methods on classification problems and investigate the effect of distributional skew on accuracy and calibration. We find that traditional post-hoc calibration falls short and some Bayesian methods are intractable for very large data. However, methods that marginalize over models give surprisingly strong results across a broad spectrum. View details
    Preview abstract Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not present in the training data. We introduce a genomics dataset for OOD detection that allows other researchers to benchmark progress on this important problem. We investigate deep generative model based approaches for OOD detection and observe that the likelihood score is heavily affected by population level background statistics. We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics. We benchmark the OOD detection performance of the proposed method against existing approaches on the genomics dataset and show that our method achieves state-of-the-art performance. We demonstrate the generality of the proposed method by showing that it significantly improves OOD detection when applied to deep generative models of images. View details
    Preview abstract We do an empirical comparison of a variety of recent methods for decision making based on deep Bayesian Neural Networks with Thompson Sampling. View details
    Preview abstract Gradient descent methods have greatly facilitated the practice of machine learning, as the learning problem can be usually represented as the minimization of a differentiable function over some parameters. However, in cases where some dependencies between parameters and variables are discrete, gradient descent cannot be applied, unless those discrete nodes are relaxed to continued values ones, where derivatives can be defined. Nonetheless, no clear solution exists in cases of structured discrete objects defined by a certain combinatorial structure; for example, in permutations, which underlie the notions of ordering, ranking and matching of objects. Here we show how to extend the relaxation method to enable gradient descent in computational graphs containing permutations as deterministic or stochastic nodes. To this end, we first show that permutations can be approximated by the differentiable Sinkhorn operator. With this, we are able to define Sinkhorn networks for the supervised learning of permutations. Finally, for stochastic nodes (corresponding to latent distributions over permutations) we introduce two implicit distributions: Gumbel-Matching and its relaxation, the Gumbel-Sinkhorn, and we prescribe how to perform inferences. We demonstrate the effectiveness of our method by showing we achieve state-of-the-art results on several tasks involving both standard datasets and a scientific application. View details
    Preview abstract Functional genomics approaches to better model genotype-phenotype relationships have important applications toward understanding genomic function and improving human health. In particular, thousands of noncoding loci associated with diseases and physical traits lack mechanistic explanation. Here, we develop the first machine-learning system to predict cell type-specific epigenetic and transcriptional profiles in large mammalian genomes from DNA sequence alone. Using convolutional neural networks, this system identifies promoters and distal regulatory elements and synthesizes their content to make effective gene expression predictions. We show that model predictions for the influence of genomic variants on gene expression align well to causal variants underlying eQTLs in human populations and can be useful for generating mechanistic hypotheses to enable GWAS loci fine mapping. View details
    Preview abstract This paper explores the problem of large-scale automatic video geolocation. A methodology is developed to infer the location at which videos from Anonymized.com were recorded using video content and various additional signals. Specifically, multiple binary Adaboost classifiers are trained to identify particular places based on learning decision stumps on sets of hundreds of thousands of sparse features. A one-vs-all classification strategy is then used to classify the location at which videos were recorded. Empirical validation is performed on an immense data set of 20 million labeled videos. Results demonstrate that high accuracy video geolocation is indeed possible for many videos and locations and interesting relationships exist between between videos and the places where they are recorded. View details
    No Results Found