English
Related papers

Related papers: Beyond the Training Distribution: Mapping Generali…

200 papers

This paper describes a way to improve the scalability of program synthesis by exploiting modularity: larger programs are synthesized from smaller programs. The key issue is to make each "larger-created-from-smaller" synthesis sub-problem be…

Programming Languages · Computer Science 2023-08-15 Kanghee Park , Keith J. C. Johnson , Loris D'Antoni , Thomas Reps

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the…

Machine Learning · Computer Science 2017-02-28 Chiyuan Zhang , Samy Bengio , Moritz Hardt , Benjamin Recht , Oriol Vinyals

Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we present a learning-theoretic framework to quantify the trade-off…

Machine Learning · Statistics 2026-04-02 Amitis Shidani , Tyler Farghly , Yang Sun , Habib Ganjgahi , George Deligiannidis

Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow…

Computation and Language · Computer Science 2024-06-03 Dylan Zhang , Justin Wang , Francois Charton

Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a…

Machine Learning · Computer Science 2020-02-14 Vikas K. Garg , Adam Kalai , Katrina Ligett , Zhiwei Steven Wu

Diffusion models generalize well in practice. However, an optimal diffusion model fully memorizes the training data and therefore fails to generalize, raising the question of what induces generalization in a real diffusion model. We show…

Machine Learning · Computer Science 2026-05-21 Tim Kaiser , Markus Kollmann

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

Computation and Language · Computer Science 2024-06-05 Henry Conklin , Kenny Smith

This paper focuses on the domain generalization task where domain knowledge is unavailable, and even worse, only samples from a single domain can be utilized during training. Our motivation originates from the recent progresses in deep…

Machine Learning · Computer Science 2022-03-08 Chris Xing Tian , Haoliang Li , Xiaofei Xie , Yang Liu , Shiqi Wang

Deep generative frameworks including GANs and normalizing flow models have proven successful at filling in missing values in partially observed data samples by effectively learning -- either explicitly or implicitly -- complex,…

Machine Learning · Computer Science 2021-04-06 Edgar A. Bernal

Can modifying the training data distribution guide optimizers toward solutions with improved generalization when training large language models (LLMs)? In this work, we theoretically analyze an in-context linear regression model with…

Machine Learning · Computer Science 2026-02-03 Tushaar Gangavarapu , Jiping Li , Christopher Vattheuer , Zhangyang Wang , Baharan Mirzasoleiman

The capacity to generalize beyond the range of training data is a pivotal challenge, often synonymous with a model's utility and robustness. This study investigates the comparative abilities of traditional machine learning (ML) models and…

Machine Learning · Computer Science 2024-03-05 Yong Yi Bay , Kathleen A. Yearick

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Machine Learning · Computer Science 2019-03-05 Jasmine Collins , Johannes Balle , Jonathon Shlens

Ensuring the generalisability of clinical machine learning (ML) models across diverse healthcare settings remains a significant challenge due to variability in patient demographics, disease prevalence, and institutional practices. Existing…

Machine Learning · Computer Science 2025-04-30 Bradley Segal , Joshua Fieggen , David Clifton , Lei Clifton

Graph transformation that predicts graph transition from one mode to another is an important and common problem. Despite much progress in developing advanced graph transformation techniques in recent years, the fundamental assumption…

Machine Learning · Computer Science 2023-05-25 Shiyu Wang , Guangji Bai , Qingyang Zhu , Zhaohui Qin , Liang Zhao

Current volumetric biomedical foundation models struggle to generalize as public 3D datasets are small and do not cover the broad diversity of medical procedures, conditions, anatomical regions, and imaging protocols. We address this by…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Neel Dey , Benjamin Billot , Hallee E. Wong , Clinton J. Wang , Mengwei Ren , P. Ellen Grant , Adrian V. Dalca , Polina Golland

Deep networks have been known to have extraordinary generalization abilities, via mechanisms that aren't yet well understood. It is also known that upon shuffling labels in the training data to varying degrees, deep networks, trained with…

Machine Learning · Computer Science 2026-03-23 Simran Ketha , Venkatakrishnan Ramaswamy

Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations.…

Machine Learning · Statistics 2021-08-19 Oguz Kaan Yuksel , Sebastian U. Stich , Martin Jaggi , Tatjana Chavdarova

For many evaluation metrics commonly used as benchmarks for unconditional image generation, trivially memorizing the training set attains a better score than models which are considered state-of-the-art; we consider this problematic. We…

Machine Learning · Computer Science 2020-01-14 Ishaan Gulrajani , Colin Raffel , Luke Metz

Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target dataset distribution. As a result, they capture only the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Zerun Wang , Jiafeng Mao , Xueting Wang , Toshihiko Yamasaki
‹ Prev 1 4 5 6 7 8 10 Next ›