Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty

Abstract

Numerous recent works utilize bi-Lipschitz regularization of neural network layers to preserve relative distances between data instances in the feature spaces of each layer. This distance sensitivity with respect to the data aids in tasks such as uncertainty calibration and out-of-distribution (OOD) detection. In previous works, features extracted with a distance sensitive model are used to construct feature covariance matrices which are used in deterministic uncertainty estimation or OOD detection. However, in cases where there is a distribution over tasks, these methods result in covariances which are sub-optimal, as they may not leverage all of the meta information which can be shared among tasks. With the use of an attentive set encoder, we propose to meta learn either diagonal or diagonal plus low-rank factors to efficiently construct task specific covariance matrices. Additionally, we propose an inference procedure which utilizes scaled energy to achieve a final predictive distribution which is well calibrated under a distributional dataset shift.

References in corpus (12)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Spectral Normalization for Generative Adversarial Networks
• On Calibration of Modern Neural Networks
• Theoretical Models of Learning to Learn
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Energy-based Out-of-distribution Detection
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• Feature Space Singularity for Out-of-Distribution Detection