paper-with-me

Papers

Correcting Predictions for Approximate Bayesian Inference

2019-09-11 · Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami

Bayesian models quantify uncertainty and facilitate optimal decision-making in downstream applications. For most models, however, practitioners are forced to use approximate inference techniques that lead to sub-optimal decisions due to incorrect posterior predictive distributions. We present a novel approach that corrects for inaccuracies in posterior inference by altering the decision-making process. We train a separate model to make optimal decisions under the approximate posterior, combining interpretable Bayesian modeling with optimization of direct predictive accuracy in a principled fashion. The solution is generally applicable as a plug-in module for predictive decision-making for arbitrary probabilistic programs, irrespective of the posterior inference strategy. We demonstrate the approach empirically in several problems, confirming its potential.

📄 PDF Abstract BibTeX arXiv:1909.04919

Code (1)

tkusmierczyk/correcting_approximate_bayesian_predictions pytorch

Tasks

Bayesian InferenceDecision Making

Similar Papers 제목 키워드 기반

Correcting Model Bias with Sparse Implicit Processes

2022-07-21 · Simón Rodríguez Santana, Luis A. Ortega, Daniel Hernández-Lobato, Bryan Zaldívar

Model selection in machine learning (ML) is a crucial part of the Bayesian learning procedure. Model choice may impose strong biases on the resulting predictions, which can hinder the performance of methods such as Bayes…

Gaussian ProcessesmodelModel Selection

Loopy Belief Propagation for Approximate Inference: An Empirical Study

2013-01-23 · Kevin Murphy, Yair Weiss, Michael. I. Jordan

Recently, researchers have demonstrated that loopy belief propagation - the use of Pearls polytree algorithm IN a Bayesian network WITH loops OF error- correcting codes.The most dramatic instance OF this IS the near Shan…

Post-hoc loss-calibration for Bayesian neural networks

2021-06-13 · Meet P. Vadera, Soumya Ghosh, Kenney Ng, Benjamin M. Marlin

Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available. Modern Bayesian models, however, typically involve intractable posterior…

Decision MakingDiversity

Nonparametric learning from Bayesian models with randomized objective functions

2018-06-29 · NeurIPS 2018 · S. P. Lyddon, S. G. Walker, C. C. Holmes

Bayesian learning is built on an assumption that the model space contains a true reflection of the data generating mechanism. This assumption is problematic, particularly in complex data environments. Here we present a B…

Nonparametric learning from Bayesian models with randomized objective functions

2018-12-01 · NeurIPS 2018 12 · Simon Lyddon, Stephen Walker, Chris C. Holmes

Bayesian learning is built on an assumption that the model space contains a true reflection of the data generating mechanism. This assumption is problematic, particularly in complex data environments. Here we present a B…