paper-with-me

Papers

A statistical theory of cold posteriors in deep neural networks

2020-08-13 · ICLR 2021 1 · Laurence Aitchison

To get Bayesian neural networks to perform comparably to standard neural networks it is usually necessary to artificially reduce uncertainty using a "tempered" or "cold" posterior. This is extremely concerning: if the prior is accurate, Bayes inference/decision theory is optimal, and any artificial changes to the posterior should harm performance. While this suggests that the prior may be at fault, here we argue that in fact, BNNs for image classification use the wrong likelihood. In particular, standard image benchmark datasets such as CIFAR-10 are carefully curated. We develop a generative model describing curation which gives a principled Bayesian account of cold posteriors, because the likelihood under this new generative model closely matches the tempered likelihoods used in past work.

📄 PDF Abstract BibTeX arXiv:2008.05912

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees

2024-10-20 · Yijie Zhang

Bayesian inference provides a principled probabilistic framework for quantifying uncertainty by updating beliefs based on prior knowledge and observed data through Bayes' theorem. In Bayesian deep learning, neural networ…

Bayesian InferenceGeneralization Bounds

Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect

2021-06-11 · NeurIPS 2021 12 · Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin 외

The "cold posterior effect" (CPE) in Bayesian deep learning describes the uncomforting observation that the predictive performance of Bayesian neural networks can be significantly improved if the Bayes posterior is artif…

Data Augmentation

How Good is the Bayes Posterior in Deep Neural Networks Really?

2020-02-06 · ICML 2020 1 · Florian Wenzel, Kevin Roth, Bastiaan S. Veeling, Jakub Świątkowski 외

During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference in deep neural networks. However, despi…

Bayesian InferenceDeep LearningUncertainty Quantification

Cold Posteriors and Aleatoric Uncertainty

2020-07-31 · Ben Adlam, Jasper Snoek, Samuel L. Smith

Recent work has observed that one can outperform exact inference in Bayesian neural networks by tuning the "temperature" of the posterior on a validation set (the "cold posterior" effect). To help interpret this phenomen…

valid

Convergence of Statistical Estimators via Mutual Information Bounds

2024-12-24 · EL Mahdi Khribch, Pierre Alquier

Recent advances in statistical learning theory have revealed profound connections between mutual information (MI) bounds, PAC-Bayesian theory, and Bayesian nonparametrics. This work introduces a novel mutual information …

Learning TheoryVariational Inference