English
Related papers

Related papers: An Online Learning Approach to Interpolation and E…

200 papers

Human visual perception can easily generalize to out-of-distributed visual data, which is far beyond the capability of modern machine learning models. Domain generalization (DG) aims to close this gap, with existing DG methods mainly…

Computer Vision and Pattern Recognition · Computer Science 2023-01-30 Bo Li , Yifei Shen , Jingkang Yang , Yezhen Wang , Jiawei Ren , Tong Che , Jun Zhang , Ziwei Liu

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are…

Environment annotations are essential for the success of many out-of-distribution (OOD) generalization methods. Unfortunately, these are costly to obtain and often limited by human annotators' biases. To achieve robust generalization, it is…

Machine Learning · Computer Science 2024-07-22 Mohammad Pezeshki , Diane Bouchacourt , Mark Ibrahim , Nicolas Ballas , Pascal Vincent , David Lopez-Paz

We consider the problem of low probability estimation: given a machine learning model and a formally-specified input distribution, how can we estimate the probability of a binary property of the model's output, even when that probability is…

Machine Learning · Computer Science 2025-02-07 Gabriel Wu , Jacob Hilton

The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce…

Optimization and Control · Mathematics 2019-07-15 Soroosh Shafieezadeh-Abadeh , Daniel Kuhn , Peyman Mohajerin Esfahani

Deep Learning systems have achieved great success in the past few years, even surpassing human intelligence in several cases. As of late, they have also established themselves in the biomedical and healthcare domains, where they have shown…

Machine Learning · Computer Science 2022-10-06 Aristotelis Ballas , Christos Diou

Deep models often fail to generalize well in test domains when the data distribution differs from that in the training domain. Among numerous approaches to address this Out-of-Distribution (OOD) generalization problem, there has been a…

Machine Learning · Computer Science 2022-10-14 Qixun Wang , Yifei Wang , Hong Zhu , Yisen Wang

Meta-learning approaches enable machine learning systems to adapt to new tasks given few examples by leveraging knowledge from related tasks. However, a large number of meta-training tasks are still required for generalization to unseen…

Machine Learning · Computer Science 2024-10-24 Seanie Lee , Bruno Andreis , Kenji Kawaguchi , Juho Lee , Sung Ju Hwang

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…

Machine Learning · Computer Science 2026-05-01 Henrik Voigt , Michael Habeck , Joachim Giesen

Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases,…

Machine Learning · Computer Science 2017-02-17 Xuezhe Ma , Yingkai Gao , Zhiting Hu , Yaoliang Yu , Yuntian Deng , Eduard Hovy

Generalization in reinforcement learning (RL) is of importance for real deployment of RL algorithms. Various schemes are proposed to address the generalization issues, including transfer learning, multi-task learning and meta learning, as…

Machine Learning · Computer Science 2022-10-07 Chang Yang , Ruiyu Wang , Xinrun Wang , Zhen Wang

We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional interaction with the environment. Specifically, we aim to…

Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Independent and Identically Distributed ($i.i.d.$). However, in…

Machine Learning · Computer Science 2023-07-28 Jiashuo Liu , Zheyan Shen , Yue He , Xingxuan Zhang , Renzhe Xu , Han Yu , Peng Cui

Reinforcement-learning (RL) agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulators produced by…

Machine Learning · Computer Science 2026-02-05 Arnaud Fickinger , Abderrahim Bendahi , Stuart Russell

In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the train and test distributions. Such models are often…

Machine Learning · Computer Science 2021-11-23 Anshul Nasery , Soumyadeep Thakur , Vihari Piratla , Abir De , Sunita Sarawagi

One of the objectives of Continual Learning is to learn new concepts continually over a stream of experiences and at the same time avoid catastrophic forgetting. To mitigate complete knowledge overwriting, memory-based methods store a…

Machine Learning · Computer Science 2023-06-21 Felipe del Rio , Julio Hurtado , Cristian Buc , Alvaro Soto , Vincenzo Lomonaco

Sequence prediction models can be learned from example sequences with a variety of training algorithms. Maximum likelihood learning is simple and efficient, yet can suffer from compounding error at test time. Reinforcement learning such as…

Machine Learning · Computer Science 2019-07-02 Bowen Tan , Zhiting Hu , Zichao Yang , Ruslan Salakhutdinov , Eric Xing

We consider bounds on the generalization performance of the least-norm linear regressor, in the over-parameterized regime where it can interpolate the data. We describe a sense in which any generalization bound of a type that is commonly…

Machine Learning · Statistics 2021-10-19 Peter L. Bartlett , Philip M. Long

While modern deep neural architectures generalise well when test data is sampled from the same distribution as training data, they fail badly for cases when the test data distribution differs from the training distribution even along a few…

Machine Learning · Computer Science 2020-10-06 Duo Wang , Mateja Jamnik , Pietro Lio

Deep neural networks (DNNs) play a crucial role in the field of machine learning, demonstrating state-of-the-art performance across various application domains. However, despite their success, DNN-based models may occasionally exhibit…

Machine Learning · Computer Science 2024-07-02 Guy Amir , Osher Maayan , Tom Zelazny , Guy Katz , Michael Schapira