English
Related papers

Related papers: When Shift Happens - Confounding Is to Blame

200 papers

We consider the problem of function estimation in the case where the data distribution may shift between training and test time, and additional information about it may be available at test time. This relates to popular scenarios such as…

Machine Learning · Statistics 2013-06-05 Bernhard Schölkopf , Dominik Janzing , Jonas Peters , Kun Zhang

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier…

Machine Learning · Computer Science 2018-04-10 Shayak Sen , Piotr Mardziel , Anupam Datta , Matthew Fredrikson

Covariate shifts are a common problem in predictive modeling on real-world problems. This paper proposes addressing the covariate shift problem by minimizing Maximum Mean Discrepancy (MMD) statistics between the training and test sets in…

Machine Learning · Computer Science 2022-03-03 Liwen Ouyang , Aaron Key

This thesis makes considerable contributions to the realm of machine learning, specifically in the context of open-world scenarios where systems face previously unseen data and contexts. Traditional machine learning models are usually…

Machine Learning · Computer Science 2023-10-11 Yiyou Sun

Question answering (QA) models are shown to be insensitive to large perturbations to inputs; that is, they make correct and confident predictions even when given largely perturbed inputs from which humans can not correctly derive answers.…

Computation and Language · Computer Science 2022-11-30 Kazutoshi Shinoda , Saku Sugawara , Akiko Aizawa

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Janis Postels , Mattia Segu , Tao Sun , Luca Sieber , Luc Van Gool , Fisher Yu , Federico Tombari

Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving novel tasks often with a few demonstrations in the prompt. These tasks require the models to generalize on distributions different from those from training…

Computation and Language · Computer Science 2024-12-31 Jiajun Song , Zhuoyan Xu , Yiqiao Zhong

We study the problem of learning personalized decision policies from observational data while accounting for possible unobserved confounding. Previous approaches, which assume unconfoundedness, i.e., that no unobserved confounders affect…

Machine Learning · Computer Science 2019-11-05 Nathan Kallus , Angela Zhou

To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained on in-distribution data. In this paper, we critically…

Machine Learning · Computer Science 2025-07-03 Yucen Lily Li , Daohan Lu , Polina Kirichenko , Shikai Qiu , Tim G. J. Rudner , C. Bayan Bruss , Andrew Gordon Wilson

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution…

Machine Learning · Computer Science 2022-09-13 Damien Teney , Ehsan Abbasnejad , Simon Lucey , Anton van den Hengel

Clinical machine learning applications are often plagued with confounders that can impact the generalizability and predictive performance of the learners. Confounding is especially problematic in remote digital health studies where the…

Grokking, or delayed generalization, is an intriguing learning phenomenon where test set loss decreases sharply only after a model's training set loss has converged. This challenges conventional understanding of the training dynamics in…

Machine Learning · Computer Science 2025-02-05 Breno W. Carvalho , Artur S. d'Avila Garcez , Luís C. Lamb , Emílio Vital Brazil

Modern foundation models exhibit remarkable out-of-distribution (OOD) generalization, solving tasks far beyond the support of their training data. However, the theoretical principles underpinning this phenomenon remain elusive. This paper…

Machine Learning · Statistics 2025-05-29 Jiawei Ge , Amanda Wang , Shange Tang , Chi Jin

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

Adversarial training may be regarded as standard training with a modified loss function. But its generalization error appears much larger than standard training under standard loss. This phenomenon, known as robust overfitting, has…

Machine Learning · Computer Science 2024-02-13 Runzhi Tian , Yongyi Mao

Convolutional networks are considered shift invariant, but it was demonstrated that their response may vary according to the exact location of the objects. In this paper we will demonstrate that most commonly investigated datasets have a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Gergely Szabo , Andras Horvath

Out-of-distribution (OOD) generalization is indispensable for learning models in the wild, where testing distribution typically unknown and different from the training. Recent methods derived from causality have shown great potential in…

Machine Learning · Computer Science 2024-05-13 Mengyue Yang , Zhen Fang , Yonggang Zhang , Yali Du , Furui Liu , Jean-Francois Ton , Jianhong Wang , Jun Wang

Predicting outcomes in external domains is challenging due to hidden confounders that potentially influence both predictors and outcomes. Well-established methods frequently rely on stringent assumptions, explicit knowledge about the…

Methodology · Statistics 2025-10-14 Carlos García Meixide , David Ríos Insua

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks…

Machine Learning · Computer Science 2023-07-07 Julia Lust , Alexandru P. Condurache

Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i)…

Machine Learning · Computer Science 2022-11-24 Matteo Pagliardini , Martin Jaggi , François Fleuret , Sai Praneeth Karimireddy