English
Related papers

Related papers: Towards Understanding Extrapolation: a Causal Lens

200 papers

We propose a new framework for binary classification in transfer learning settings where both covariate and label distributions may shift between source and target domains. Unlike traditional covariate shift or label shift assumptions, we…

Methodology · Statistics 2025-09-29 Manli Cheng , Subha Maity , Qinglong Tian , Pengfei Li

We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data. In particular, we consider simple…

Machine Learning · Statistics 2022-06-17 Chen Cheng , John Duchi , Rohith Kuditipudi

Limited overlap between treated and control groups is a key challenge in observational analysis. Standard approaches like trimming importance weights can reduce variance but introduce a fundamental bias. We propose a sensitivity framework…

Machine Learning · Statistics 2026-04-21 Yuanzhe Ma , Yian Huang , Hongseok Namkoong

In implicit models, one often interpolates between sampled points in latent space. As we show in this paper, care needs to be taken to match-up the distributional assumptions on code vectors with the geometry of the interpolating paths.…

Machine Learning · Computer Science 2018-02-05 Yannic Kilcher , Aurelien Lucchi , Thomas Hofmann

Data assimilation refers to the problem of finding trajectories of a prescribed dynamical model in such a way that the output of the model (usually some function of the model states) follows a given time series of observations. Typically…

Atmospheric and Oceanic Physics · Physics 2015-05-30 Jochen Bröcker , Ivan G. Szendro

When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is…

Machine Learning · Computer Science 2022-05-10 Penny Chong , Ngai-Man Cheung , Yuval Elovici , Alexander Binder

Treatment effect estimation, which refers to the estimation of causal effects and aims to measure the strength of the causal relationship, is of great importance in many fields but is a challenging problem in practice. As present,…

Machine Learning · Computer Science 2021-07-20 Zhenyu Guo , Shuai Zheng , Zhizhe Liu , Kun Yan , Zhenfeng Zhu

We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Kenneth Borup , Cheng Perng Phoo , Bharath Hariharan

Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g.…

Machine Learning · Computer Science 2019-03-13 Yifan Wu , Ezra Winston , Divyansh Kaushik , Zachary Lipton

Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in…

Machine Learning · Statistics 2019-03-01 Adarsh Subbaswamy , Peter Schulam , Suchi Saria

One of the most critical problems in transfer learning is the task of domain adaptation, where the goal is to apply an algorithm trained in one or more source domains to a different (but related) target domain. This paper deals with domain…

Machine Learning · Computer Science 2021-12-08 Mohammad Ali Javidian , Om Pandey , Pooyan Jamshidi

When learning a mapping from an input space to an output space, the assumption that the sample distribution of the training data is the same as that of the test data is often violated. Unsupervised domain shift methods adapt the learned…

Machine Learning · Computer Science 2017-03-07 Tomer Galanti , Lior Wolf

We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model. The target dataset is often assumed to be fully identifiable in a standard unlearning scenario. Such…

Machine Learning · Computer Science 2023-03-15 Youngsik Yoon , Jinhwan Nam , Hyojeong Yun , Jaeho Lee , Dongwoo Kim , Jungseul Ok

Despite the burgeoning body of work on distribution shifts, provenance shift-where the relationship between data source and label changes at deployment-remains poorly understood and under-addressed. In this paper, we establish a formal…

Machine Learning · Computer Science 2026-05-13 Yongsen Tan , Zhecheng Sheng , Xiruo Ding , Serguei V. S. Pakhomov , Trevor Cohen

Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of linear regression a…

Machine Learning · Computer Science 2024-08-28 Neil Mallinar , Austin Zane , Spencer Frei , Bin Yu

Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…

Machine Learning · Computer Science 2023-11-08 Zhijie Deng , Peng Cui , Jun Zhu

Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often…

Machine Learning · Computer Science 2025-06-26 Lan-Cuong Nguyen , Quan Nguyen-Tri , Bang Tran Khanh , Dung D. Le , Long Tran-Thanh , Khoat Than

While neural networks can be trained to map from one specific dataset to another, they usually do not learn a generalized transformation that can extrapolate accurately outside the space of training. For instance, a generative adversarial…

Quantitative Methods · Quantitative Biology 2019-01-25 Matthew Amodio , David van Dijk , Ruth Montgomery , Guy Wolf , Smita Krishnaswamy

Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data,…

Computer Vision and Pattern Recognition · Computer Science 2020-02-19 Yann Lifchitz , Yannis Avrithis , Sylvaine Picard

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Recently, self-supervised representation learning techniques (via contrastive learning…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Sina Mohseni , Arash Vahdat , Jay Yadawa
‹ Prev 1 4 5 6 7 8 10 Next ›