English
Related papers

Related papers: A Generalized Spectral Framework to Expain Neural …

200 papers

Proposing an effective and flexible matrix to represent a graph is a fundamental challenge that has been explored from multiple perspectives, e.g., filtering in Graph Fourier Transforms. In this work, we develop a novel and general…

Machine Learning · Computer Science 2023-05-11 Mingqi Yang , Wenjie Feng , Yanming Shen , Bryan Hooi

Grokking typically achieves similar loss to ordinary, "steady", learning. We ask whether these different learning paths - grokking versus ordinary training - lead to fundamental differences in the learned models. To do so we compare the…

Neural scaling laws suggest that the test error of large language models trained online decreases polynomially as the model size and data size increase. However, such scaling can be unsustainable when running out of new data. In this work,…

Machine Learning · Computer Science 2025-09-26 Licong Lin , Jingfeng Wu , Peter L. Bartlett

While data-driven methods offer significant promise for modeling complex materials, they often face challenges in generalizing across diverse physical scenarios and maintaining physical consistency. To address these limitations, we propose…

Graphics · Computer Science 2025-10-27 Xueguang Xie , Shu Yan , Shiwen Jia , Siyu Yang , Aimin Hao , Yang Gao , Peng Yu

Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original data or expensive re-computation. Despite empirical successes, a unified theory for…

Machine Learning · Computer Science 2026-03-20 Qinglun Li , Anke Tang , Miao Zhang , Mengzhu Wang , Quanjun Yin , Li Shen

We develop a data-driven framework for discovering constitutive relations in models of fluid flow and scalar transport. Under the assumption that velocity and/or scalar fields are measured, our approach infers unknown closure terms in the…

Fluid Dynamics · Physics 2026-01-01 Suguru Shiratori , Elham Kiyani , Khemraj Shukla , George Em Karniadakis

Generalization abilities of well-trained large language models (LLMs) are known to scale predictably as a function of model size. In contrast to the existence of practical scaling laws governing pre-training, the quality of LLMs after…

Machine Learning · Computer Science 2024-12-09 Zifei Xu , Alexander Lan , Wanzin Yazar , Tristan Webb , Sayeh Sharify , Xin Wang

We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to…

Machine Learning · Statistics 2017-06-01 Yuichi Yoshida , Takeru Miyato

The scaling exponent $\alpha$ in neural scaling laws $L(N) \propto N^{-\alpha}$ is commonly treated as a fixed constant set by architecture and data. We present evidence that $\alpha$ depends systematically on the optimizer. In controlled…

Machine Learning · Computer Science 2026-05-29 Vansh Ramani , Shourya Vir Jain

Recent work has shown that, in generative modeling, cross-entropy loss improves smoothly with model size and training compute, following a power law plus constant scaling law. One challenge in extending these results to reinforcement…

Machine Learning · Computer Science 2023-02-21 Jacob Hilton , Jie Tang , John Schulman

We study the compute-optimal trade-off between model and training data set sizes for large neural networks. Our result suggests a linear relation similar to that supported by the empirical analysis of chinchilla. While that work studies…

Machine Learning · Computer Science 2023-10-20 Hong Jun Jeon , Benjamin Van Roy

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…

Machine Learning · Statistics 2022-11-10 Wenjing Yang , Ganghua Wang , Jie Ding , Yuhong Yang

Dimensionality reduction is critical for deploying dense retrieval systems at scale, yet mainstream post-hoc methods face a fundamental trade-off: principal component analysis (PCA) preserves dominant variance but underutilizes…

Information Retrieval · Computer Science 2026-04-20 Yongkang Li , Panagiotis Eustratiadis , Evangelos Kanoulas

The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networks. Nevertheless, the functional form of this dependency…

Machine Learning · Computer Science 2019-12-23 Jonathan S. Rosenfeld , Amir Rosenfeld , Yonatan Belinkov , Nir Shavit

Distributed learning provides an attractive framework for scaling the learning task by sharing the computational load over multiple nodes in a network. Here, we investigate the performance of distributed learning for large-scale linear…

Machine Learning · Statistics 2021-11-03 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with minimal effort.…

Machine Learning · Computer Science 2020-05-19 Yerlan Idelbayev , Miguel Á. Carreira-Perpiñán

The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source condition, noise level and choice of the regularization parameter rather than the minimax…

Machine Learning · Computer Science 2024-11-26 Yicheng Li , Weiye Gan , Zuoqiang Shi , Qian Lin

Can neural networks systematically capture discrete, compositional task structure despite their continuous, distributed nature? The impressive capabilities of large-scale neural networks suggest that the answer to this question is yes.…

Machine Learning · Computer Science 2025-10-27 Florian Redhardt , Yassir Akram , Simon Schug

Neural scaling laws aim to characterize how out-of-sample error behaves as a function of model and training dataset size. Such scaling laws guide allocation of a computational resources between model and data processing to minimize error.…

Machine Learning · Computer Science 2024-07-02 Hong Jun Jeon , Benjamin Van Roy

Diffusion models are powerful generative models that produce high-quality samples from complex data. While their infinite-data behavior is well understood, their generalization with finite data remains less clear. Classical learning theory…

Machine Learning · Statistics 2026-02-02 Claudia Merger , Sebastian Goldt
‹ Prev 1 4 5 6 7 8 10 Next ›