paper-with-me

Papers

Locking and Quacking: Stacking Bayesian model predictions by log-pooling and superposition

2023-05-12 · Yuling Yao, Luiz Max Carvalho, Diego Mesquita, Yann McLatchie

Combining predictions from different models is a central problem in Bayesian inference and machine learning more broadly. Currently, these predictive distributions are almost exclusively combined using linear mixtures such as Bayesian model averaging, Bayesian stacking, and mixture of experts. Such linear mixtures impose idiosyncrasies that might be undesirable for some applications, such as multi-modality. While there exist alternative strategies (e.g. geometric bridge or superposition), optimising their parameters usually involves computing an intractable normalising constant repeatedly. We present two novel Bayesian model combination tools. These are generalisations of model stacking, but combine posterior densities by log-linear pooling (locking) and quantum superposition (quacking). To optimise model weights while avoiding the burden of normalising constants, we investigate the Hyvarinen score of the combined posterior predictions. We demonstrate locking with an illustrative example and discuss its practical application with importance sampling.

📄 PDF Abstract BibTeX arXiv:2305.07334

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceMixture-of-Experts

Similar Papers 제목 키워드 기반

Bayesian hierarchical stacking: Some models are (somewhere) useful

2021-01-22 · Yuling Yao, Gregor Pirš, Aki Vehtari, Andrew Gelman

Stacking is a widely used model averaging technique that asymptotically yields optimal predictions among linear averages. We show that stacking is most effective when model predictive performance is heterogeneous in inpu…

Bayesian InferenceTime SeriesTime Series Analysis

Bayesian Regression Approach for Building and Stacking Predictive Models in Time Series Analytics

2022-01-06 · Bohdan M. Pavlyshenko

The paper describes the use of Bayesian regression for building time series models and stacking different predictive models for time series. Using Bayesian regression for time series modeling with nonlinear trend was ana…

Decision MakingregressionTime SeriesTime Series Analysis+1

BayesBlend: Easy Model Blending using Pseudo-Bayesian Model Averaging, Stacking and Hierarchical Stacking in Python

2024-04-30 · Nathaniel Haines, Conor Goold

Averaging predictions from multiple competing inferential models frequently outperforms predictions from any single model, providing that models are optimally weighted to maximize predictive performance. This is particul…

model

An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networks

2022-01-27 · Dominik Müller, Iñaki Soto-Rey, Frank Kramer

Novel and high-performance medical image classification pipelines are heavily utilizing ensemble learning strategies. The idea of ensemble learning is to assemble diverse models or multiple predictions and, thus, boost p…

ClassificationEnsemble LearningImage Augmentationimage-classification+3

Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support

2023-10-23 · Tim Reichelt, Luke Ong, Tom Rainforth

The posterior in probabilistic programs with stochastic support decomposes as a weighted sum of the local posterior distributions associated with each possible program path. We show that making predictions with this full…