English
Related papers

Related papers: Perturb and Correct: Post-Hoc Ensembles using Affi…

200 papers

This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show…

Machine Learning · Computer Science 2020-07-01 Jize Zhang , Bhavya Kailkhura , T. Yong-Jin Han

Uncertainty quantification is critical in safety-sensitive applications but is often omitted from off-the-shelf neural networks due to adverse effects on predictive performance. Retrofitting uncertainty estimates post-hoc typically requires…

Machine Learning · Computer Science 2025-06-03 Lennart Bramlage , Cristóbal Curio

Although deep neural networks yield high classification accuracy given sufficient training data, their predictions are typically overconfident or under-confident, i.e., the prediction confidences cannot truly reflect the accuracy. Post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Jiexin Wang , Jiahao Chen , Bing Su

Combining machine learning and constrained optimization, Predict+Optimize tackles optimization problems containing parameters that are unknown at the time of solving. Prior works focus on cases with unknowns only in the objectives. A new…

Machine Learning · Computer Science 2023-03-14 Xinyi Hu , Jasper C. H. Lee , Jimmy H. M. Lee

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. However, high computational and storage demands hinder their deployment into resource-constrained environments, such as embedded…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Pallavi Mitra , Gesina Schwalbe , Nadja Klein

Deep unsupervised anomaly detection has seen improvements in a supervised binary classification paradigm in which auxiliary external data is included in the training set as anomalous data in a process referred to as outlier exposure, which…

Machine Learning · Computer Science 2025-03-26 Sean Gloumeau

The generalization ability of machine learning models degrades significantly when the test distribution shifts away from the training distribution. We investigate the problem of training models that are robust to shifts caused by changes in…

Machine Learning · Computer Science 2023-09-19 Jiaheng Wei , Harikrishna Narasimhan , Ehsan Amid , Wen-Sheng Chu , Yang Liu , Abhishek Kumar

Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…

Machine Learning · Computer Science 2024-10-17 Linwei Tao , Haolan Guo , Minjing Dong , Chang Xu

Recent models for natural language understanding are inclined to exploit simple patterns in datasets, commonly known as shortcuts. These shortcuts hinge on spurious correlations between labels and latent features existing in the training…

Computation and Language · Computer Science 2024-11-19 Ukyo Honda , Tatsushi Oka , Peinan Zhang , Masato Mita

Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This…

Machine Learning · Computer Science 2020-09-10 Maruan Al-Shedivat , Avinava Dubey , Eric P. Xing

Probability calibration for deep models is highly desirable in safety-critical applications such as medical imaging. It makes output probabilities of deep networks interpretable, by aligning prediction probability with the actual accuracy…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Cheng Ouyang , Shuo Wang , Chen Chen , Zeju Li , Wenjia Bai , Bernhard Kainz , Daniel Rueckert

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the \texttt{Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift} challenge. We find that…

Machine Learning · Computer Science 2024-01-10 Sankalp Gilda , Neel Bhandari , Wendy Mak , Andrea Panizza

When transferring a pretrained model to a downstream task, two popular methods are full fine-tuning (updating all the model parameters) and linear probing (updating only the last linear layer -- the "head"). It is well known that…

Machine Learning · Computer Science 2022-02-24 Ananya Kumar , Aditi Raghunathan , Robbie Jones , Tengyu Ma , Percy Liang

Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretrained models either inherit misplaced confidence or merely…

Machine Learning · Computer Science 2025-09-30 Charmaine Barker , Daniel Bethell , Simos Gerasimou

Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their…

Software Engineering · Computer Science 2026-05-20 Ravishka Rathnasuriya , Wei Yang

Some recent works observed the instability of post-hoc explanations when input side perturbations are applied to the model. This raises the interest and concern in the stability of post-hoc explanations. However, the remaining question is:…

Computation and Language · Computer Science 2022-12-13 Ruixuan Tang , Hanjie Chen , Yangfeng Ji

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

Machine Learning · Computer Science 2025-06-26 Eugène Berta , David Holzmüller , Michael I. Jordan , Francis Bach

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…

Machine Learning · Computer Science 2023-08-09 Susu Sun , Lisa M. Koch , Christian F. Baumgartner

Deep neural networks often develop spurious bias, reliance on correlations between non-essential features and classes for predictions. For example, a model may identify objects based on frequently co-occurring backgrounds rather than…

Machine Learning · Computer Science 2025-06-02 Guangtao Zheng , Wenqian Ye , Aidong Zhang

Post-hoc calibration of pre-trained models is critical for ensuring reliable inference, especially in safety-critical domains such as healthcare. Conformal Prediction (CP) offers a robust post-hoc calibration framework, providing…

Machine Learning · Computer Science 2025-05-22 Haifeng Wen , Hong Xing , Osvaldo Simeone