English
Related papers

Related papers: When and How Mixup Improves Calibration

200 papers

As algorithms increasingly inform and influence decisions made about individuals, it becomes increasingly important to address concerns that these algorithms might be discriminatory. The output of an algorithm can be discriminatory for many…

Machine Learning · Computer Science 2018-03-19 Úrsula Hébert-Johnson , Michael P. Kim , Omer Reingold , Guy N. Rothblum

Collaborative training can improve the accuracy of a model for a user by trading off the model's bias (introduced by using data from other users who are potentially different) against its variance (due to the limited amount of data on any…

Machine Learning · Computer Science 2022-06-24 El Mahdi Chayti , Sai Praneeth Karimireddy , Sebastian U. Stich , Nicolas Flammarion , Martin Jaggi

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Zhijun Mai , Guosheng Hu , Dexiong Chen , Fumin Shen , Heng Tao Shen

Training a classification model on a dataset where the instances of one class outnumber those of the other class is a challenging problem. Such imbalanced datasets are standard in real-world situations such as fraud detection, medical…

Machine Learning · Computer Science 2020-09-04 Anubha Kabra , Ayush Chopra , Nikaash Puri , Pinkesh Badjatiya , Sukriti Verma , Piyush Gupta , Balaji K

Overfitting & underfitting and stable training are an important challenges in machine learning. Current approaches for these issues are mixup, SamplePairing and BC learning. In our work, we state the hypothesis that mixing many images…

Machine Learning · Computer Science 2020-01-22 Maciej A. Czyzewski

Artificial intelligence(AI)-assisted method had received much attention in the risk field such as disease diagnosis. Different from the classification of disease types, it is a fine-grained task to classify the medical images as benign or…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Shuang Ge , Kehong Yuan , Maokun Han , Desheng Sun , Huabin Zhang , Qiongyu Ye

We study the connection between multicalibration and boosting for squared error regression. First we prove a useful characterization of multicalibration in terms of a ``swap regret'' like condition on squared error. Using this…

Machine Learning · Computer Science 2023-02-01 Ira Globus-Harris , Declan Harrison , Michael Kearns , Aaron Roth , Jessica Sorrell

Data augmentation methods, especially SoTA interpolation-based methods such as Fair Mixup, have been widely shown to increase model fairness. However, this fairness is evaluated on metrics that do not capture model uncertainty and on…

Machine Learning · Computer Science 2025-04-16 Karina Halevy , Karly Hou , Charumathi Badrinath

Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art…

Computation and Language · Computer Science 2019-05-23 Hongyu Guo , Yongyi Mao , Richong Zhang

This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks for calibration not just marginally, but simultaneously…

Machine Learning · Statistics 2024-04-09 Gianluca Detommaso , Martin Bertran , Riccardo Fogliato , Aaron Roth

This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks. For the future advance of NER in safety-critical fields like healthcare and finance, it is…

Computation and Language · Computer Science 2024-10-28 Wataru Hashimoto , Hidetaka Kamigaito , Taro Watanabe

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

Machine Learning · Computer Science 2022-07-08 Gregory Scafarto , Nicolas Posocco , Antoine Bonnefoy

To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often…

Computation and Language · Computer Science 2026-04-21 Yuxin Xiao , Shujian Zhang , Wenxuan Zhou , Marzyeh Ghassemi , Sanqiang Zhao

Multicalibration gradient boosting has recently emerged as a scalable method that empirically produces approximately multicalibrated predictors and has been deployed at web scale. Despite this empirical success, its convergence properties…

Machine Learning · Computer Science 2026-02-09 Daniel Haimovich , Fridolin Linder , Lorenzo Perini , Niek Tax , Milan Vojnovic

Text classification tasks often encounter few shot scenarios with limited labeled data, and addressing data scarcity is crucial. Data augmentation with mixup has shown to be effective on various text classification tasks. However, most of…

Computation and Language · Computer Science 2023-11-28 Haoqi Zheng , Qihuang Zhong , Liang Ding , Zhiliang Tian , Xin Niu , Dongsheng Li , Dacheng Tao

Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are…

Machine Learning · Computer Science 2023-11-03 Wenxuan Bao , Francesco Pittaluga , Vijay Kumar B G , Vincent Bindschaedler

Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the confidence score alone. However, this view can hide substantial structure: models may be…

Machine Learning · Computer Science 2026-05-14 Katarzyna Kobalczyk , Mihaela van der Schaar

Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD. In this work, we report a…

Machine Learning · Computer Science 2023-03-03 Zixuan Liu , Ziqiao Wang , Hongyu Guo , Yongyi Mao

Accurate probabilistic predictions can be characterized by two properties -- calibration and sharpness. However, standard maximum likelihood training yields models that are poorly calibrated and thus inaccurate -- a 90% confidence interval…

Machine Learning · Computer Science 2025-05-14 Volodymyr Kuleshov , Shachi Deshpande

In typical machine learning systems, an estimate of the probability of the prediction is used to assess the system's confidence in the prediction. This confidence measure is usually uncalibrated; i.e.\ the system's confidence in the…

Computation and Language · Computer Science 2022-05-24 Shehzaad Dhuliawala , Leonard Adolphs , Rajarshi Das , Mrinmaya Sachan
‹ Prev 1 3 4 5 6 7 10 Next ›