Posterior Uncertainty Quantification in Neural Networks using Data Augmentation
In this paper, we approach the problem of uncertainty quantification in deep learning through a predictive framework, which captures uncertainty in model parameters by specifying our assumptions about the predictive distribution of unseen future data. Under this view, we show that deep ensembling (Lakshminarayanan et al., 2017) is a fundamentally mis-specified model class, since it assumes that future data are supported on existing observations only -- a situation rarely encountered in practice. To address this limitation, we propose MixupMP, a method that constructs a more realistic predictive distribution using popular data augmentation techniques. MixupMP operates as a drop-in replacement for deep ensembles, where each ensemble member is trained on a random simulation from this predictive distribution. Grounded in the recently-proposed framework of Martingale posteriors (Fong et al., 2023), MixupMP returns samples from an implicitly defined Bayesian posterior. Our empirical analysis showcases that MixupMP achieves superior predictive performance and uncertainty quantification on various image classification datasets, when compared with existing Bayesian and non-Bayesian approaches.
Code (1)
Tasks
Data Augmentationimage-classificationImage ClassificationUncertainty QuantificationSimilar Papers 제목 키워드 기반
Uncertainty Quantification for Prior-Data Fitted Networks using Martingale Posteriors
Prior-data fitted networks (PFNs) have emerged as promising foundation models for prediction from tabular data sets, achieving state-of-the-art performance on small to moderate data sizes without tuning. While PFNs are m…
Uncertainty QuantificationQuantification of Uncertainty with Adversarial Models
Quantifying uncertainty is important for actionable predictions in real-world applications. A crucial part of predictive uncertainty quantification is the estimation of epistemic uncertainty, which is defined as an integ…
Spectral Representations for Accurate Causal Uncertainty Quantification with Gaussian Processes
Accurate uncertainty quantification for causal effects is essential for robust decision making in complex systems, but remains challenging in non-parametric settings. One promising framework represents conditional distri…
Bayesian OptimisationDecision MakingGaussian ProcessesUncertainty QuantificationNeuralSurv: Deep Survival Analysis with Bayesian Uncertainty Quantification
We introduce NeuralSurv, the first deep survival model to incorporate Bayesian uncertainty quantification. Our non-parametric, architecture-agnostic framework flexibly captures time-varying covariate-risk relationships i…
Data AugmentationSurvival AnalysisUncertainty QuantificationCUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks
In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been pr…
Node ClassificationUncertainty Quantification