中文
相关论文

相关论文: The Missing Invariance Principle Found -- the Reci…

200 篇论文

Empirical Risk Minimization (ERM) based machine learning algorithms have suffered from weak generalization performance on data obtained from out-of-distribution (OOD). To address this problem, Invariant Risk Minimization (IRM) objective was…

机器学习 · 计算机科学 2021-03-25 Jun-Hyun Bae , Inchul Choi , Minho Lee

Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain…

机器学习 · 计算机科学 2021-03-30 Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski

Machine learning models traditionally assume that training and test data are independently and identically distributed. However, in real-world applications, the test distribution often differs from training. This problem, known as…

机器学习 · 计算机科学 2024-06-19 Kotaro Yoshida , Hiroki Naganuma

The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The underlying assumption is that the causal components of the…

机器学习 · 计算机科学 2021-12-28 Moulik Choraria , Ibtihal Ferwana , Ankur Mani , Lav R. Varshney

This work considers the out-of-distribution (OOD) prediction problem where (1)~the training data are from multiple domains and (2)~the test domain is unseen in the training. DNNs fail in OOD prediction because they are prone to pick up…

机器学习 · 计算机科学 2021-02-24 Ruocheng Guo , Pengchuan Zhang , Hao Liu , Emre Kiciman

Invariant risk minimization (IRM) is an arising approach to generalize invariant features to different environments in machine learning. While most related works focus on new IRM settings or new application scenarios, the mathematical…

机器学习 · 计算机科学 2024-05-20 Zhao-Rong Lai , Weiwen Wang

The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) generalization failures. Despite the promising theory, invariance…

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top…

机器学习 · 统计学 2020-03-31 Martin Arjovsky , Léon Bottou , Ishaan Gulrajani , David Lopez-Paz

We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" form, and even on very simple problems which directly follow…

机器学习 · 统计学 2021-03-02 Pritish Kamath , Akilesh Tangella , Danica J. Sutherland , Nathan Srebro

Invariant risk minimization (IRM) aims to enable out-of-distribution (OOD) generalization in deep learning by learning invariant representations. As IRM poses an inherently challenging bi-level optimization problem, most existing approaches…

机器学习 · 计算机科学 2025-05-26 Kotaro Yoshida , Konstantinos Slavakis

Deep learning models excel in computer vision tasks but often fail to generalize to out-of-distribution (OOD) domains. Invariant Risk Minimization (IRM) aims to address OOD generalization by learning domain-invariant features. However, IRM…

计算机视觉与模式识别 · 计算机科学 2025-01-24 Yaoyao Zhu , Xiuding Cai , Yingkai Wang , Dong Miao , Zhongliang Fu , Xu Luo

Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk minimization (IRM) is a recent proposal for discovering…

机器学习 · 计算机科学 2023-10-24 Francesco Alesiani , Shujian Yu , Mathias Niepert

Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments.…

机器学习 · 计算机科学 2023-04-04 Moulik Choraria , Ibtihal Ferwana , Ankur Mani , Lav R. Varshney

Invariant risk minimization (IRM) (Arjovsky et al., 2019) is a recently proposed framework designed for learning predictors that are invariant to spurious correlations across different training environments. Yet, despite its theoretical…

机器学习 · 统计学 2020-07-07 Yo Joong Choe , Jiyeon Ham , Kyubyong Park

The performance of machine learning models can be impacted by changes in data over time. A promising approach to address this challenge is invariant learning, with a particular focus on a method known as invariant risk minimization (IRM).…

机器学习 · 计算机科学 2024-04-09 Wenlu Tang , Zicheng Liu

Machine learning algorithms with empirical risk minimization usually suffer from poor generalization performance due to the greedy exploitation of correlations among the training data, which are not stable under distributional shifts.…

机器学习 · 计算机科学 2021-06-18 Jiashuo Liu , Zheyuan Hu , Peng Cui , Bo Li , Zheyan Shen

Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be preferred over the widely-employed empirical risk minimization…

机器学习 · 计算机科学 2022-08-22 Kartik Ahuja , Jun Wang , Amit Dhurandhar , Karthikeyan Shanmugam , Kush R. Varshney

Deep Neural Networks often inherit spurious correlations embedded in training data and hence may fail to generalize to unseen domains, which have different distributions from the domain to provide training data. M. Arjovsky et al. (2019)…

机器学习 · 统计学 2024-10-30 Shoji Toyota , Kenji Fukumizu

Learning invariant (causal) features for out-of-distribution (OOD) generalization has attracted extensive attention recently, and among the proposals invariant risk minimization (IRM) is a notable solution. In spite of its theoretical…

机器学习 · 计算机科学 2023-02-01 Bin Deng , Kui Jia

We propose a novel unsupervised framework for \emph{Invariant Risk Minimization} (IRM), extending the concept of invariance to settings where labels are unavailable. Traditional IRM methods rely on labeled data to learn representations that…

机器学习 · 计算机科学 2026-03-05 Yotam Norman , Ron Meir
‹ 上一页 1 2 3 10 下一页 ›