English
Related papers

Related papers: Pretrained Transformers Improve Out-of-Distributio…

200 papers

Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models as even subtle changes could incur significant performance drops. Being able to estimate a model's performance on test data is important in practice…

Machine Learning · Computer Science 2023-02-13 Yuzhe Lu , Zhenlin Wang , Runtian Zhai , Soheil Kolouri , Joseph Campbell , Katia Sycara

The generalization ability of machine learning models degrades significantly when the test distribution shifts away from the training distribution. We investigate the problem of training models that are robust to shifts caused by changes in…

Machine Learning · Computer Science 2023-09-19 Jiaheng Wei , Harikrishna Narasimhan , Ehsan Amid , Wen-Sheng Chu , Yang Liu , Abhishek Kumar

Models trained with deep learning often fail to signal when inputs fall outside their training data manifold, leading to unreliable predictions under distribution shift. Prior work suggests that effective out-of-distribution (OOD) detection…

Machine Learning · Computer Science 2026-05-08 Brett Barkley , Preston Culbertson , David Fridovich-Keil

We study in-context learning problems where a Transformer is pretrained on tasks drawn from a mixture distribution $\pi=\sum_{\alpha\in\mathcal{A}} \lambda_{\alpha} \pi_{\alpha}$, called the pretraining prior, in which each mixture…

Machine Learning · Statistics 2026-05-08 Tianyi Ma , Tengyao Wang , Richard J. Samworth

Recent years have witnessed significant progress in the development of machine learning models across a wide range of fields, fueled by increased computational resources, large-scale datasets, and the rise of deep learning architectures.…

Neural networks, while effective for tackling many challenging scientific tasks, are not known to perform well out-of-distribution (OOD), i.e., within domains which differ from their training data. Understanding neural network OOD…

Machine Learning · Computer Science 2025-12-11 Luis Rangel DaCosta , Mary C. Scott

Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its training distribution using quantities available prior to test-time evaluation. Building on the…

Interpretability research often aims to predict how a model will respond to targeted interventions on specific mechanisms. However, it rarely predicts how a model will respond to unseen input data. This paper explores the promises and…

Machine Learning · Computer Science 2025-07-10 Victoria R. Li , Jenny Kaufmann , Martin Wattenberg , David Alvarez-Melis , Naomi Saphra

Out-of-distribution generalization (OODG) is a longstanding challenge for neural networks. This challenge is quite apparent in tasks with well-defined variables and rules, where explicit use of the rules could solve problems independently…

Machine Learning · Computer Science 2022-12-14 Andrew J. Nam , Mustafa Abdool , Trevor Maxfield , James L. McClelland

In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks.…

Machine Learning · Computer Science 2023-03-21 Sadegh Mahdavi , Kevin Swersky , Thomas Kipf , Milad Hashemi , Christos Thrampoulidis , Renjie Liao

With recent advancements in artificial intelligence, its applications can be seen in every aspect of humans' daily life. From voice assistants to mobile healthcare and autonomous driving, we rely on the performance of AI methods for many…

Machine Learning · Computer Science 2022-09-28 Navid Ghassemi , Ehsan Fazl-Ersi

Out-of-distribution generalization can be categorized into two types: common perturbations arising from natural variations in the real world and adversarial perturbations that are intentionally crafted to deceive neural networks. While deep…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Fatemeh Amerehi , Patrick Healy

Neural networks are often utilised in critical domain applications (e.g. self-driving cars, financial markets, and aerospace engineering), even though they exhibit overconfident predictions for ambiguous inputs. This deficiency demonstrates…

Machine Learning · Computer Science 2023-01-03 John Mitros , Brian Mac Namee

Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types of adversarial OOD…

Machine Learning · Computer Science 2021-07-01 Jiefeng Chen , Yixuan Li , Xi Wu , Yingyu Liang , Somesh Jha

Accurate de novo molecular and materials design requires structure-property models that generalize beyond known regimes. Although pretrained atomistic models achieve strong in-distribution accuracy after fine-tuning, their reliability under…

Computational Physics · Physics 2026-01-14 Chengqian Zhang , Duo Zhang , Anyang Peng , Mingyu Guo , Yuzhi Zhang , Lei Wang , Guolin Ke , Linfeng Zhang , Tiejun Li , Han Wang

While additional training data improves the robustness of deep neural networks against adversarial examples, it presents the challenge of curating a large number of specific real-world samples. We circumvent this challenge by using…

Machine Learning · Computer Science 2022-03-04 Vikash Sehwag , Saeed Mahloujifar , Tinashe Handina , Sihui Dai , Chong Xiang , Mung Chiang , Prateek Mittal

Certified robustness guarantee gauges a model's robustness to test-time attacks and can assess the model's readiness for deployment in the real world. In this work, we critically examine how the adversarial robustness guarantees from…

Machine Learning · Computer Science 2021-12-02 Jiachen Sun , Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Dan Hendrycks , Jihun Hamm , Z. Morley Mao

Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text. This paper…

Computation and Language · Computer Science 2025-03-27 Tianhao Wu , Yu Wang , Ngoc Quach

Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in…

Artificial Intelligence · Computer Science 2025-10-15 Wissam Salhab , Darine Ameyed , Hamid Mcheick , Fehmi Jaafar

Modern AI models excel in controlled settings but often fail in real-world scenarios where data distributions shift unpredictably - a challenge known as domain generalisation (DG). This paper tackles this limitation by rigorously evaluating…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Hamza Riaz , Alan F. Smeaton