paper-with-me

홈 › Papers

Stationary Activations for Uncertainty Calibration in Deep Learning

2020-10-19 · NeurIPS 2020 12 · Lassi Meronen, Christabella Irwanto, Arno Solin

We introduce a new family of non-linear neural network activation functions that mimic the properties induced by the widely-used Mat\'ern family of kernels in Gaussian process (GP) models. This class spans a range of locally stationary models of various degrees of mean-square differentiability. We show an explicit link to the corresponding GP models in the case that the network consists of one infinitely wide hidden layer. In the limit of infinite smoothness the Mat\'ern family results in the RBF kernel, and in this case we recover RBF activations. Mat\'ern activation functions result in similar appealing properties to their counterparts in GP models, and we demonstrate that the local stationarity property together with limited mean-square differentiability shows both good performance and uncertainty calibration in Bayesian deep learning tasks. In particular, local stationarity helps calibrate out-of-distribution (OOD) uncertainty. We demonstrate these properties on classification and regression benchmarks and a radar emitter classification task.

📄 PDF Abstract BibTeX arXiv:2010.09494

Code (1)

AaltoML/stationary-activations 공식 구현 pytorch

Tasks

Deep LearningGeneral Classification

Methods 이 논문이 사용한 방법론

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

Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach

2024-04-24 · Linyu Liu, Yu Pan, Xiaocheng Li, Guanting Chen

In this paper, we study the problem of uncertainty estimation and calibration for LLMs. We begin by formulating the uncertainty estimation problem, a relevant yet underexplored area in existing literature. We then propos…

Activation-Space Uncertainty Quantification for Pretrained Networks

2026-02-16 · Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez, Jonathan Plenk 외 arxiv

Reliable uncertainty estimates are crucial for deploying pretrained models; yet, many strong methods for quantifying uncertainty require retraining, Monte Carlo sampling, or expensive second-order computations and may al…

Out-of-Distribution DetectionImage Segmentation

Adaptive Multi-Scale Forecasting and Gate-Localized Conformal Prediction for Multivariate Nonstationary Time Series

2026-07-25 · Ziling Ma, Junshu Jiang, Ángel López-Oriona, Ying Sun 외 arxiv

We propose ABF-T-GLCP, a model-agnostic framework for forecasting and uncertainty quantification in nonstationary multivariate time series. The central idea is to learn an adaptive predictive state representation for poi…

Reading Calibrated Uncertainty from Language Model Trajectories

2026-05-19 · Aliai Eusebi, Alexander Herzog, Xiaoyu Liang, Marie Vasek 외 arxiv

The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with structured output. Although cheap, it is often miscalibrated. Methods that…

Feature Separation and Recalibration for Adversarial Robustness

2023-03-24 · CVPR 2023 1 · Woo Jae Kim, Yoonki Cho, Junsik Jung, Sung-Eui Yoon

Deep neural networks are susceptible to adversarial attacks due to the accumulation of perturbations in the feature level, and numerous works have boosted model robustness by deactivating the non-robust feature activatio…

Adversarial AttackAdversarial Robustness