paper-with-me

홈 › Papers

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 suggest to fix this by considering an infinite number of ReLU features over the input domain that are never part of the training process and thus remain at prior values. Perhaps surprisingly, we show that this model leads to a tractable Gaussian process (GP) term that can be added to a pre-trained BNN's posterior at test time with negligible cost overhead. The BNN then yields structured uncertainty in the proximity of training data, while the GP prior calibrates uncertainty far away from them. As a key contribution, we prove that the added uncertainty yields cubic predictive variance growth, and thus the ideal uniform (maximum entropy) confidence in multi-class classification far from the training data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-class Classification

Similar Papers 제목 키워드 기반

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 overconf…

Multi-class Classification

Uncertainty Quantification for Sparse Deep Learning

2020-02-26 · Yuexi Wang, Veronika Ročková

Deep learning methods continue to have a decided impact on machine learning, both in theory and in practice. Statistical theoretical developments have been mostly concerned with approximability or rates of estimation whe…

Deep LearningUncertainty Quantificationvalid

Student-t processes as infinite-width limits of posterior Bayesian neural networks

2025-02-06 · Francesco Caporali, Stefano Favaro, Dario Trevisan

The asymptotic properties of Bayesian Neural Networks (BNNs) have been extensively studied, particularly regarding their approximations by Gaussian processes in the infinite-width limit. We extend these results by showin…

Gaussian Processes

Approximation speed of quantized vs. unquantized ReLU neural networks and beyond

2022-05-24 · Antoine Gonon, Nicolas Brisebarre, Rémi Gribonval, Elisa Riccietti

We deal with two complementary questions about approximation properties of ReLU networks. First, we study how the uniform quantization of ReLU networks with real-valued weights impacts their approximation properties. We …

Quantization

Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables

2019-11-01 · Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Bayesian Neural Networks with Latent Variables (BNN+LVs) capture predictive uncertainty by explicitly modeling model uncertainty (via priors on network weights) and environmental stochasticity (via a latent input noise v…