English
Related papers

Related papers: When to Retrain after Drift: A Data-Only Test of P…

200 papers

Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yilin Zhang , Cai Xu , You Wu , Ziyu Guan , Wei Zhao

The performance of machine learning (ML) models often deteriorates when the underlying data distribution changes over time, a phenomenon known as data distribution drift. When this happens, ML models need to be retrained and redeployed. ML…

Machine Learning · Computer Science 2025-12-15 Emmanuel K. Katalay , David O. Dimandja , Jordan F. Masakuna

Concept drift -- the change of the distribution over time -- poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thus paramount, and drift localization -- determining which…

Machine Learning · Computer Science 2026-04-22 Fabian Hinder , Valerie Vaquet , Johannes Brinkrolf , Barbara Hammer

Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because uncertainty reliability can degrade earlier and more sharply…

Machine Learning · Computer Science 2026-04-28 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it…

Machine Learning · Computer Science 2022-07-19 Meena Jagadeesan , Tijana Zrnic , Celestine Mendler-Dünner

Machine learning approaches for image classification have led to impressive advances in that field. For example, convolutional neural networks are able to achieve remarkable image classification accuracy across a wide range of applications…

Machine Learning · Statistics 2025-10-30 Christopher T. Franck , Anne R. Driscoll , Zoe Szajnfarber , William H. Woodall

Mining data streams is one of the main studies in machine learning area due to its application in many knowledge areas. One of the major challenges on mining data streams is concept drift, which requires the learner to discard the current…

Machine Learning · Computer Science 2023-04-20 Jean Paul Barddal , Heitor Murilo Gomes , Fabrício Enembreck

The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models may become inaccurate and need adjustment. Many technologies for…

Machine Learning · Computer Science 2022-12-05 Fabian Hinder , Valerie Vaquet , Johannes Brinkrolf , Barbara Hammer

Concept drift refers to gradual or sudden changes in the properties of data that affect the accuracy of machine learning models. In this paper, we address the problem of concept drift detection in the malware domain. Specifically, we…

Machine Learning · Computer Science 2026-03-17 Aniket Mishra , Mark Stamp

Deep learning is envisioned to facilitate the operation of wireless receivers, with emerging architectures integrating deep neural networks (DNNs) with traditional modular receiver processing. While deep receivers were shown to operate…

Information Theory · Computer Science 2024-07-15 Nicole Uzlaner , Tomer Raviv , Nir Shlezinger , Koby Todros

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Despite rapid progress in Vision-Language-Action (VLA) models for robotic control, instruction drift remains a persistent failure mode in long-horizon tasks. This paper reconceptualizes this phenomenon, positing that instruction drift is…

Robotics · Computer Science 2026-05-12 Kewei Chen , Yayu Long , Mingsheng Shang

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Zichao Li , Cihang Xie , Ekin Dogus Cubuk

Online Learning (OL) is a field of research that is increasingly gaining attention both in academia and industry. One of the main challenges of OL is the inherent presence of concept drifts, which are commonly defined as unforeseeable…

Machine Learning · Computer Science 2024-07-01 Mauro Dalle Lucca Tosi , Martin Theobald

Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on…

Machine Learning · Computer Science 2021-04-27 Łukasz Korycki , Bartosz Krawczyk

Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduction in computation cost for inference by using…

Computer Vision and Pattern Recognition · Computer Science 2019-05-17 Kentaro Yoshioka , Edward Lee , Simon Wong , Mark Horowitz

Detecting drifts in data is essential for machine learning applications, as changes in the statistics of processed data typically has a profound influence on the performance of trained models. Most of the available drift detection methods…

Machine Learning · Computer Science 2024-10-28 Andrea Castellani , Sebastian Schmitt , Barbara Hammer

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of…

Software Engineering · Computer Science 2024-05-21 Hao Li , Gopi Krishnan Rajbahadur , Dayi Lin , Cor-Paul Bezemer , Zhen Ming , Jiang

Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-to-hard…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Hieu Tran Bao , Nguyen Cong Dat , Nguyen Duc Anh , Hoang Thanh-Tung