Active Recursive Bayesian Inference with Posterior Trajectory Analysis Using α-Divergence

04/07/2020
by   Yeganeh M. Marghi, et al.
4

Recursive Bayesian inference (RBI) provides optimal Bayesian latent variable estimates in real-time settings with streaming noisy observations. Active RBI attempts to effectively select queries that lead to more informative observations to rapidly reduce uncertainty until a confident decision is made. However, typically the optimality objectives of inference and query mechanisms are not jointly selected. Furthermore, conventional active querying methods stagger due to misleading prior information. Motivated by information theoretic approaches, we propose an active RBI framework with unified inference and query selection steps through Renyi entropy and α-divergence. We also propose a new objective based on Renyi entropy and its changes called Momentum that encourages exploration for misleading prior cases. The proposed active RBI framework is applied to the trajectory of the posterior changes in the probability simplex that provides a coordinated active querying and decision making with specified confidence. Under certain assumptions, we analytically demonstrate that the proposed approach outperforms conventional methods such as mutual information by allowing the selections of unlikely events. We present empirical and experimental performance evaluations on two applications: restaurant recommendation and brain-computer interface (BCI) typing systems.

READ FULL TEXT
research
05/24/2023

Adversarial robustness of amortized Bayesian inference

Bayesian inference usually requires running potentially costly inference...
research
01/30/2022

Causal inference under mis-specification: adjustment based on the propensity score

We study Bayesian approaches to causal inference via propensity score re...
research
05/15/2023

Bayesian inference for misspecified generative models

Bayesian inference is a powerful tool for combining information in compl...
research
02/03/2017

Query Efficient Posterior Estimation in Scientific Experiments via Bayesian Active Learning

A common problem in disciplines of applied Statistics research such as A...
research
06/05/2018

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

We formalize the problem of learning interdomain correspondences in the ...
research
07/28/2018

Prior-Proposal Recursive Bayesian Inference

Bayesian models are naturally equipped to provide recursive inference be...
research
06/05/2022

Information Threshold, Bayesian Inference and Decision-Making

We define the information threshold as the point of maximum curvature in...

Please sign up or login with your details

Forgot password? Click here to reset