paper-with-me

Papers

Can a Confident Prior Replace a Cold Posterior?

2024-03-02 · Martin Marek, Brooks Paige, Pavel Izmailov

Benchmark datasets used for image classification tend to have very low levels of label noise. When Bayesian neural networks are trained on these datasets, they often underfit, misrepresenting the aleatoric uncertainty of the data. A common solution is to cool the posterior, which improves fit to the training data but is challenging to interpret from a Bayesian perspective. We explore whether posterior tempering can be replaced by a confidence-inducing prior distribution. First, we introduce a "DirClip" prior that is practical to sample and nearly matches the performance of a cold posterior. Second, we introduce a "confidence prior" that directly approximates a cold likelihood in the limit of decreasing temperature but cannot be easily sampled. Lastly, we provide several general insights into confidence-inducing priors, such as when they might diverge and how fine-tuning can mitigate numerical instability.

📄 PDF Abstract BibTeX arXiv:2403.01272

Code (1)

martin-marek/dirclip 공식 구현 jax

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

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

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 pr…

image-classificationImage Classification

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

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

If there is no underfitting, there is no Cold Posterior Effect

2023-10-02 · Yijie Zhang, Yi-Shan Wu, Luis A. Ortega, Andrés R. Masegosa

The cold posterior effect (CPE) (Wenzel et al., 2020) in Bayesian deep learning shows that, for posteriors with a temperature $T<1$, the resulting posterior predictive could have better performances than the Bayesian pos…