Work

Affine invariant ensemble transform methods to improve predictive uncertainty in neural networks

Year: 2024

Type: article

Abstract: We consider the problem of performing Bayesian inference for logistic regression using appropriate extensions of the ensemble Kalman filter. Two interacting particle systems are proposed that sample from an approximate posterior and prove quantitative convergence rates of these interacting particle systems to their mean-field limit as the number of particles tends to infinity. Furthermore, we apply these techniques and examine their effectiveness as methods of Bayesian approximation for quantifying predictive uncertainty in neural networks.

Source: Foundations of Data Science

DOI: 10.3934/fods.2024040

Authors: Diksha Bhandari, Jakiw Pidstrigach, Sebastian Reich

Institution: University of Potsdam

Language: English

Topic: Markov Chains and Monte Carlo Methods

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: diamond

Funders: Deutsche Forschungsgemeinschaft, Engineering and Physical Sciences Research Council, Division of Mathematical Sciences