As deep learning models are increasingly deployed in high-stakes applications, providing well-calibrated uncertainty estimates has become as critical as achieving high predictive accuracy. While Kernel Density Estimation (KDE) has emerged as a smooth and continuous alternative to traditional binning for quantifying miscalibration, its reliability is heavily dependent on the choice of the kernel bandwidth.
arXiv:2602. 13362v2 Announce Type: replace-cross Abstract: A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty.
By \'Ad\'am Jung, Domokos M. Kelen, Andr\'as A. Bencz\'ur
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
By Ange-Cl\'ement Akazan, Ineza Remy Mugenga, Abebe Geletu, Jean Medard Ngnotchouye, Issa Karambal
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
By Eug\`ene Berta, David Holzm\"uller, Francis Bach, Michael I. Jordan
arXiv:2606. 16214v1 Announce Type: cross Abstract: Modern deep learning models remain notoriously prone to overconfidence, limiting their reliability in high-stakes applications.
By Tobias Jan Wieczorek, Leon de Andrade, Thomas M\"ollenhoff, Marcus Rohrbach
The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.
By Haolan Guo, Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu
arXiv:2608.30230v1 Announce Type: new
Abstract: Test-time prompt tuning (TPT) has emerged as a powerful paradigm, refining prompts for each test sample via entropy minimization (EM) over multiple aug...
By Jungwon Choi, Hyeonseo Jang, Kibok Lee, Eunwoo Kim
arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.
By Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge
arXiv:2209. 01754v5 Announce Type: replace-cross Abstract: The empirical risk minimization approach to data-driven decision making requires access to training data drawn under the same conditions as those that will be faced when the decision rule is deployed.
By Roshni Sahoo, Lihua Lei, Stefan Wager
arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.
By Lening Zhao, Qipeng Zhan, Li Shen
Detecting out-of-distribution (OOD) data is crucial for reliable machine learning deployment. Among detection strategies, post-hoc methods are particularly attractive due to their efficiency, as they operate directly on pre-trained networks without requiring retraining.
arXiv:2607. 28248v1 Announce Type: cross Abstract: The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification.
By H. Martin Gillis, Thomas Trappenberg