paper-with-me

Papers

A Variational View on Bootstrap Ensembles as Bayesian Inference

2020-06-08 · Dimitrios Milios, Pietro Michiardi, Maurizio Filippone

In this paper, we employ variational arguments to establish a connection between ensemble methods for Neural Networks and Bayesian inference. We consider an ensemble-based scheme where each model/particle corresponds to a perturbation of the data by means of parametric bootstrap and a perturbation of the prior. We derive conditions under which any optimization steps of the particles makes the associated distribution reduce its divergence to the posterior over model parameters. Such conditions do not require any particular form for the approximation and they are purely geometrical, giving insights on the behavior of the ensemble on a number of interesting models such as Neural Networks with ReLU activations. Experiments confirm that ensemble methods can be a valid alternative to approximate Bayesian inference; the theoretical developments in the paper seek to explain this behavior.

📄 PDF Abstract BibTeX arXiv:2006.04548

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inferencevalid

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Parametric Bootstrap Ensembles as Variational Inference

2020-11-23 · pproximateinference AABI Symposium 2021 1 · Dimitrios Milios, Pietro Michiardi, Maurizio Filippone

In this paper, we employ variational arguments to establish a connection between ensemble methods for Neural Networks and Bayesian inference. We consider an ensemble-based scheme where each model/particle corresponds to …

Bayesian InferenceVariational Inference

A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods

2023-05-24 · NeurIPS 2023 11 · Veit David Wild, Sahra Ghalebikesabi, Dino Sejdinovic, Jeremias Knoblauch

We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods. A key step towards this it to reformulate the non-convex optimisation problem typically encountered in dee…

Deep LearningUncertainty QuantificationVariational Inference

Deep Ensembles: A Loss Landscape Perspective

2019-12-05 · Stanislav Fort, Huiyi Hu, Balaji Lakshminarayanan

Deep ensembles have been empirically shown to be a promising approach for improving accuracy, uncertainty and out-of-distribution robustness of deep learning models. While deep ensembles were theoretically motivated by t…

Bayesian posterior approximation with stochastic ensembles

2022-12-15 · CVPR 2023 1 · Oleksandr Balabanov, Bernhard Mehlig, Hampus Linander

We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochastic ensembles are formulated as families of distrib…

Bayesian Inferenceimage-classificationImage ClassificationVariational Inference

On the use of bootstrap with variational inference: Theory, interpretation, and a two-sample test example

2017-11-29 · Yen-Chi Chen, Y. Samuel Wang, Elena A. Erosheva

Variational inference is a general approach for approximating complex density functions, such as those arising in latent variable models, popular in machine learning. It has been applied to approximate the maximum likeli…

Bayesian InferenceVariational Inference