Multivariate Bayesian Last Layer for Regression: Uncertainty Quantification and Disentanglement
We present new Bayesian Last Layer models in the setting of multivariate regression under heteroscedastic noise, and propose an optimization algorithm for parameter learning. Bayesian Last Layer combines Bayesian modelling of the predictive distribution with neural networks for parameterization of the prior, and has the attractive property of uncertainty quantification with a single forward pass. The proposed framework is capable of disentangling the aleatoric and epistemic uncertainty, and can be used to transfer a canonically trained deep neural network to new data domains with uncertainty-aware capability.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementregressionUncertainty QuantificationSimilar Papers 제목 키워드 기반
Improved uncertainty quantification for neural networks with Bayesian last layer
Uncertainty quantification is an important task in machine learning - a task in which standardneural networks (NNs) have traditionally not excelled. This can be a limitation for safety-critical applications, where uncert…
Gaussian ProcessesregressionUncertainty QuantificationVariational InferenceVariational Bayesian Last Layers
We introduce a deterministic variational formulation for training Bayesian last layer neural networks. This yields a sampling-free, single-pass model and loss that effectively improves uncertainty estimation. Our variati…
Out-of-Distribution DetectionVariational InferenceRicher Bayesian Last Layers with Subsampled NTK Features
Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underestimate epistemic uncertainty because they apply a Bayesian treatment onl…
Out-of-Distribution DetectionImage ClassificationBayesian Linear Regression on Deep Representations
A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent work [Riquelme et al., 2018, Azizzadenesh…
Model-based Reinforcement Learningregressionreinforcement-learningReinforcement Learning+1Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last laye…
Computational EfficiencyOut-of-Distribution DetectionUncertainty Quantification