paper-with-me

홈 › Papers

An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence

2020-10-06 · NeurIPS 2021 12 · Agustinus Kristiadi, Matthias Hein, Philipp Hennig

A Bayesian treatment can mitigate overconfidence in ReLU nets around the training data. But far away from them, ReLU Bayesian neural networks (BNNs) can still underestimate uncertainty and thus be asymptotically overconfident. This issue arises since the output variance of a BNN with finitely many features is quadratic in the distance from the data region. Meanwhile, Bayesian linear models with ReLU features converge, in the infinite-width limit, to a particular Gaussian process (GP) with a variance that grows cubically so that no asymptotic overconfidence can occur. While this may seem of mostly theoretical interest, in this work, we show that it can be used in practice to the benefit of BNNs. We extend finite ReLU BNNs with infinite ReLU features via the GP and show that the resulting model is asymptotically maximally uncertain far away from the data while the BNNs' predictive power is unaffected near the data. Although the resulting model approximates a full GP posterior, thanks to its structure, it can be applied \emph{post-hoc} to any pre-trained ReLU BNN at a low cost.

📄 PDF Abstract BibTeX arXiv:2010.02709

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-class Classification

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…
Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization

2021-06-07 · NeurIPS 2021 12 · Mufan Bill Li, Mihai Nica, Daniel M. Roy

Theoretical results show that neural networks can be approximated by Gaussian processes in the infinite-width limit. However, for fully connected networks, it has been previously shown that for any fixed network width, $…

Gaussian Processes

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features

2020-09-28 · Agustinus Kristiadi, Matthias Hein, Philipp Hennig

Approximate Bayesian methods can mitigate overconfidence in ReLU networks. However, far away from the training data, even Bayesian neural networks (BNNs) can still underestimate uncertainty and thus be overconfident. We …

Multi-class Classification

Approximating Continuous Functions by ReLU Nets of Minimal Width

2017-10-31 · Boris Hanin, Mark Sellke

This article concerns the expressive power of depth in deep feed-forward neural nets with ReLU activations. Specifically, we answer the following question: for a fixed $d_{in}\geq 1,$ what is the minimal width $w$ so tha…

De-randomized PAC-Bayes Margin Bounds: Applications to Non-convex and Non-smooth Predictors

2020-02-23 · Arindam Banerjee, Tiancong Chen, Yingxue Zhou

In spite of several notable efforts, explaining the generalization of deterministic non-smooth deep nets, e.g., ReLU-nets, has remained challenging. Existing approaches for deterministic non-smooth deep nets typically ne…

Generalization Bounds

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks

2020-12-21 · Quynh Nguyen, Marco Mondelli, Guido Montufar

A recent line of work has analyzed the theoretical properties of deep neural networks via the Neural Tangent Kernel (NTK). In particular, the smallest eigenvalue of the NTK has been related to the memorization capacity, …

Memorization