A view on model misspecification in uncertainty quantification

2022-10-30 · Yuko Kato, David M. J. Tax, Marco Loog

Estimating uncertainty of machine learning models is essential to assess the quality of the predictions that these models provide. However, there are several factors that influence the quality of uncertainty estimates, one of which is the amount of model misspecification. Model misspecification always exists as models are mere simplifications or approximations to reality. The question arises whether the estimated uncertainty under model misspecification is reliable or not. In this paper, we argue that model misspecification should receive more attention, by providing thought experiments and contextualizing these with relevant literature.

📄 PDF Abstract BibTeX arXiv:2210.16938

Code (0)

등록된 구현이 없습니다.

Tasks

modelUncertainty Quantification

Robust Deep Gaussian Processes

2019-04-04 · Jeremias Knoblauch

This report provides an in-depth overview over the implications and novelty Generalized Variational Inference (GVI) (Knoblauch et al., 2019) brings to Deep Gaussian Processes (DGPs) (Damianou & Lawrence, 2013). Specifica…

Gaussian Processes Uncertainty Quantification Variational Inference

Quantification of total uncertainty in the physics-informed reconstruction of CVSim-6 physiology

2024-08-13 · Mario De Florio, Zongren Zou, Daniele E. Schiavazzi, George Em Karniadakis

When predicting physical phenomena through simulation, quantification of the total uncertainty due to multiple sources is as crucial as making sure the underlying numerical model is accurate. Possible sources include irr…

Form Uncertainty Quantification

Strategic Conformal Prediction

2024-11-03 · Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert

When a machine learning model is deployed, its predictions can alter its environment, as better informed agents strategize to suit their own interests. With such alterations in mind, existing approaches to uncertainty qu…

Conformal Prediction Prediction Uncertainty Quantification

Uncertainty quantification using martingales for misspecified Gaussian processes

2020-06-12 · Willie Neiswanger, Aaditya Ramdas

We address uncertainty quantification for Gaussian processes (GPs) under misspecified priors, with an eye towards Bayesian Optimization (BO). GPs are widely used in BO because they easily enable exploration based on post…

Bayesian Optimization Gaussian Processes Uncertainty Quantification valid

Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework

2025-02-02 · Terje Mildner, Oliver Hamelijnck, Paris Giampouras, Theodoros Damoulas

We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentist and Bayesian FL by providing unbiased …

Federated Learning Uncertainty Quantification Variational Inference