English
Related papers

Related papers: Generalization vs. Specialization under Concept Sh…

200 papers

Despite achieving excellent performance on benchmarks, deep neural networks often underperform in real-world deployment due to sensitivity to minor, often imperceptible shifts in input data, known as distributional shifts. These shifts are…

Machine Learning · Computer Science 2025-09-25 Birk Torpmann-Hagen , Pål Halvorsen , Michael A. Riegler , Dag Johansen

Learning from weak, proxy, or relative supervision is common when ground-truth labels are unavailable, but robustness under distribution shift remains poorly understood because the supervision mechanism itself may change across…

Machine Learning · Computer Science 2026-05-20 Mehrdad Shoeibi , Elias Hossain , Ivan Garibay , Niloofar Yousefi

National statistical institutes currently investigate how to improve the output quality of official statistics based on machine learning algorithms. A key obstacle is concept drift, i.e., when the joint distribution of independent variables…

Methodology · Statistics 2021-03-02 Quinten Meertens , Cees Diks , Jaap van den Herik , Frank Takes

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic…

Machine Learning · Computer Science 2026-01-21 Hong Zheng , Fei Teng

Distribution shifts on graphs -- the discrepancies in data distribution between training and employing a graph machine learning model -- are ubiquitous and often unavoidable in real-world scenarios. These shifts may severely deteriorate…

Machine Learning · Computer Science 2025-03-31 Kexin Zhang , Shuhan Liu , Song Wang , Weili Shi , Chen Chen , Pan Li , Sheng Li , Jundong Li , Kaize Ding

In the field of Machine Learning (ML) and data-driven applications, one of the significant challenge is the change in data distribution between the training and deployment stages, commonly known as distribution shift. This paper outlines…

Machine Learning · Computer Science 2025-07-30 Lakpa Tamang , Mohamed Reda Bouadjenek , Richard Dazeley , Sunil Aryal

Investigation of machine learning algorithms robust to changes between the training and test distributions is an active area of research. In this paper we explore a special type of dataset shift which we call class-dependent domain shift.…

Machine Learning · Computer Science 2020-07-13 Tigran Galstyan , Hrant Khachatrian , Greg Ver Steeg , Aram Galstyan

Machine learning models are omnipresent for predictions on big data. One challenge of deployed models is the change of the data over time, a phenomenon called concept drift. If not handled correctly, a concept drift can lead to significant…

Machine Learning · Computer Science 2020-04-02 Lucas Baier , Marcel Hofmann , Niklas Kühl , Marisa Mohr , Gerhard Satzger

Time series prediction is often complicated by distribution shift which demands adaptive models to accommodate time-varying distributions. We frame time series prediction under distribution shift as a weighted empirical risk minimisation…

Machine Learning · Computer Science 2022-07-26 Stefanos Bennett , Jase Clarkson

This paper studies transfer learning for ridge-regularized robust linear regression in the moderate-dimensional regime, where the number of predictors is of the same order as the sample size and the regression coefficients are not assumed…

Methodology · Statistics 2026-04-14 Lingfeng Lyu , Xiao Guo , Zongqi Liu

Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its performance. Therefore, maintaining a constant monitoring…

Computation and Language · Computer Science 2023-09-08 Saeed Khaki , Akhouri Abhinav Aditya , Zohar Karnin , Lan Ma , Olivia Pan , Samarth Marudheri Chandrashekar

Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How does such…

Machine Learning · Computer Science 2026-05-19 Afiq Abdillah Effiezal Aswadi , Oliver Britton , Ross Baker , Matthew Farrugia-Roberts

An open scientific challenge is how to classify events with reliable measures of uncertainty, when we have a mechanistic model of the data-generating process but the distribution over both labels and latent nuisance parameters is different…

Machine Learning · Statistics 2024-07-02 Luca Masserano , Alex Shen , Michele Doro , Tommaso Dorigo , Rafael Izbicki , Ann B. Lee

Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to…

Machine Learning · Computer Science 2025-05-28 Abbavaram Gowtham Reddy , Celia Rubio-Madrigal , Rebekka Burkholz , Krikamol Muandet

In this paper, we investigate the phenomenon of grokking, where models exhibit delayed generalization following overfitting on training data. We focus on data-scarce regimes where the number of training samples falls below the critical…

Machine Learning · Computer Science 2025-11-10 Vaibhav Singh , Eugene Belilovsky , Rahaf Aljundi

A growing number of machine learning scenarios rely on knowledge distillation where one uses the output of a surrogate model as labels to supervise the training of a target model. In this work, we provide a sharp characterization of this…

Machine Learning · Statistics 2025-02-28 M. Emrullah Ildiz , Halil Alperen Gozeten , Ege Onur Taga , Marco Mondelli , Samet Oymak

Generalization is a central problem in Machine Learning. Indeed most prediction methods require careful calibration of hyperparameters usually carried out on a hold-out \textit{validation} dataset to achieve generalization. The main goal of…

Machine Learning · Statistics 2021-02-18 Karim Lounici , Katia Meziani , Benjamin Riu

Predictive models are typically trained on historical data to predict future outcomes. While it is commonly assumed that training on more historical data would improve model performance and robustness, data distribution shifts over time may…

Computers and Society · Computer Science 2025-09-05 Chengyuan Yao , Yunxuan Tang , Christopher Brooks , Rene F. Kizilcec , Renzhe Yu

A trained ML model is deployed on another `test' dataset where target feature values (labels) are unknown. Drift is distribution change between the training and deployment data, which is concerning if model performance changes. For a…

Applications · Statistics 2022-09-07 Samuel Ackerman , Eitan Farchi , Orna Raz , Marcel Zalmanovici , Parijat Dube

Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are well-exercised within the available training environments. We introduce a simple robust…

Machine Learning · Computer Science 2021-10-20 Yilun Xu , Tommi Jaakkola