paper-with-me

홈 › Papers

Norm-Based Capacity Control in Neural Networks

2015-02-27 · Behnam Neyshabur, Ryota Tomioka, Nathan Srebro

We investigate the capacity, convexity and characterization of a general family of norm-constrained feed-forward networks.

📄 PDF Abstract BibTeX arXiv:1503.00036

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units

2018-10-03 · NeurIPS 2018 12 · Yixi Xu, Xiao Wang

This paper presents a general framework for norm-based capacity control for $L_{p,q}$ weight normalized deep neural networks. We establish the upper bound on the Rademacher complexities of this family. With an $L_{p,q}$ …

The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control

2025-11-02 · Khoat Than arxiv

Normalization layers are critical components of modern AI systems, such as ChatGPT, Gemini, DeepSeek, etc. Empirically, they are known to stabilize training dynamics and improve generalization ability. However, the under…

Capacity Control of ReLU Neural Networks by Basis-path Norm

2018-09-19 · Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen 외

Recently, path norm was proposed as a new capacity measure for neural networks with Rectified Linear Unit (ReLU) activation function, which takes the rescaling-invariant property of ReLU into account. It has been shown t…

The Shape of Generalization through the Lens of Norm-based Capacity Control

2025-02-03 · Yichen Wang, Yudong Chen, Lorenzo Rosasco, Fanghui Liu

Understanding how the test risk scales with model complexity is a central question in machine learning. Classical theory is challenged by the learning curves observed for large over-parametrized deep networks. Capacity m…

DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models

2023-06-20 · Sidi Lu, Wenbo Zhao, Chenyang Tao, Arpit Gupta 외

NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving guaranteed convergence to an entropy-maximi…

Machine Translation