English
Related papers

Related papers: Too Sharp, Too Sure: When Calibration Follows Curv…

200 papers

Confidence calibration is central to providing accurate and interpretable uncertainty estimates, especially under safety-critical scenarios. However, we find that existing calibration algorithms often overlook the issue of *proximity bias*,…

Machine Learning · Computer Science 2024-03-19 Miao Xiong , Ailin Deng , Pang Wei Koh , Jiaying Wu , Shen Li , Jianqing Xu , Bryan Hooi

Although sparse training has been successfully used in various resource-limited deep learning tasks to save memory, accelerate training, and reduce inference time, the reliability of the produced sparse models remains unexplored. Previous…

Machine Learning · Computer Science 2023-03-02 Bowen Lei , Ruqi Zhang , Dongkuan Xu , Bani Mallick

Calibration measures and reliability diagrams are two fundamental tools for measuring and interpreting the calibration of probabilistic predictors. Calibration measures quantify the degree of miscalibration, and reliability diagrams…

Machine Learning · Computer Science 2023-09-22 Jarosław Błasiok , Preetum Nakkiran

Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve the quality of the confidence levels, also known as…

Machine Learning · Computer Science 2024-04-15 Jiayi Huang , Sangwoo Park , Osvaldo Simeone

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario,…

Machine Learning · Computer Science 2019-10-30 Armin Eftekhari , ChaeHwan Song , Volkan Cevher

Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is crucial for risk…

Machine Learning · Computer Science 2023-01-11 Gabriella Chouraqui , Liron Cohen , Gil Einziger , Liel Leman

Despite Graph Neural Networks (GNNs) have achieved remarkable accuracy, whether the results are trustworthy is still unexplored. Previous studies suggest that many modern neural networks are over-confident on the predictions, however,…

Machine Learning · Computer Science 2022-01-05 Xiao Wang , Hongrui Liu , Chuan Shi , Cheng Yang

Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially…

Machine Learning · Computer Science 2025-08-08 Wenhao Liang , Chang Dong , Liangwei Zheng , Wei Zhang , Weitong Chen

We introduce a framework for calibrating machine learning models so that their predictions satisfy explicit, finite-sample statistical guarantees. Our calibration algorithms work with any underlying model and (unknown) data-generating…

Machine Learning · Computer Science 2022-10-03 Anastasios N. Angelopoulos , Stephen Bates , Emmanuel J. Candès , Michael I. Jordan , Lihua Lei

In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify…

Machine Learning · Computer Science 2019-06-25 Zhilu Zhang , Adrian V. Dalca , Mert R. Sabuncu

Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications. Recent advances in representation learning have led to considerable improvements in this area. Many state of the art…

Computer Vision and Pattern Recognition · Computer Science 2018-10-29 Zhiding Yu , Weiyang Liu , Yang Zou , Chen Feng , Srikumar Ramalingam , B. V. K. Vijaya Kumar , Jan Kautz

Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses serious challenges in applications where reliable uncertainty…

Machine Learning · Computer Science 2025-09-12 Pedro Mendes , Paolo Romano , David Garlan

Handling uncertainty is critical for ensuring reliable decision-making in intelligent systems. Modern neural networks are known to be poorly calibrated, resulting in predicted confidence scores that are difficult to use. This article…

Machine Learning · Computer Science 2026-05-18 Gabriele Sanguin , Arjun Pakrashi , Marco Viola , Francesco Rinaldi

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

Neural networks sometimes exhibit grokking, a phenomenon where perfect or near-perfect performance is achieved on a validation set well after the same performance has been obtained on the corresponding training set. In this workshop paper,…

Machine Learning · Computer Science 2024-02-15 Jack Miller , Patrick Gleeson , Charles O'Neill , Thang Bui , Noam Levi

To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies have shown that tail…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yanbiao Ma , Licheng Jiao , Fang Liu , Maoji Wen , Lingling Li , Wenping Ma , Shuyuan Yang , Xu Liu , Puhua Chen

The ability to ensure that a classifier gives reliable confidence scores is essential to ensure informed decision-making. To this end, recent work has focused on miscalibration, i.e., the over or under confidence of model scores. Yet…

Machine Learning · Computer Science 2023-04-28 Alexandre Perez-Lebel , Marine Le Morvan , Gaël Varoquaux

Consider a multi-class labelling problem, where the labels can take values in $[k]$, and a predictor predicts a distribution over the labels. In this work, we study the following foundational question: Are there notions of multi-class…

Machine Learning · Computer Science 2024-06-11 Parikshit Gopalan , Lunjia Hu , Guy N. Rothblum

With the advancement of deep learning technology, neural networks have demonstrated their excellent ability to provide accurate predictions in many tasks. However, a lack of consideration for neural network calibration will not gain trust…

Machine Learning · Computer Science 2022-11-30 Lei Hsiung , Yung-Chen Tang , Pin-Yu Chen , Tsung-Yi Ho

Uncertainty estimates must be calibrated (i.e., accurate) and sharp (i.e., informative) in order to be useful. This has motivated a variety of methods for recalibration, which use held-out data to turn an uncalibrated model into a…

Machine Learning · Computer Science 2022-07-06 Charles Marx , Shengjia Zhao , Willie Neiswanger , Stefano Ermon