paper-with-me

홈 › Papers

Spectrally-normalized margin bounds for neural networks

2017-06-26 · NeurIPS 2017 12 · Peter Bartlett, Dylan J. Foster, Matus Telgarsky

This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for a standard AlexNet network trained with SGD on the mnist and cifar10 datasets, with both original and random labels; the bound, the Lipschitz constants, and the excess risks are all in direct correlation, suggesting both that SGD selects predictors whose complexity scales with the difficulty of the learning task, and secondly that the presented bound is sensitive to this complexity.

📄 PDF Abstract BibTeX arXiv:1706.08498

Code (1)

mostafaelaraby/generalization-gap-features-tensorflow tf

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

2017-07-29 · ICLR 2018 1 · Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro

We present a generalization bound for feedforward neural networks in terms of the product of the spectral norm of the layers and the Frobenius norm of the weights. The generalization bound is derived using a PAC-Bayes an…

Improving Generalization of Deep Neural Networks by Leveraging Margin Distribution

2018-12-27 · ICLR 2019 5 · Shen-Huan Lyu, Lu Wang, Zhi-Hua Zhou

Recent research has used margin theory to analyze the generalization performance for deep neural networks (DNNs). The existed results are almost based on the spectrally-normalized minimum margin. However, optimizing the …

Representation Learning

Rethinking Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics

2018-10-08 · Weizhi Zhu, Yifei HUANG, Yuan YAO

Margin enlargement over training data has been an important strategy since perceptrons in machine learning for the purpose of boosting the robustness of classifiers toward a good generalization ability. Yet Breiman (1999…

Generalization Bounds

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

2023-10-09 · NeurIPS 2023 11

Deep neural networks (DNNs) are vulnerable to adversarial attacks. It is found empirically that adversarially robust generalization is crucial in establishing defense algorithms against adversarial attacks. Therefore, it…

Adversarial RobustnessGeneralization Bounds

ON BREIMAN’S DILEMMA IN NEURAL NETWORKS: SUCCESS AND FAILURE OF NORMALIZED MARGINS

2019-05-01 · ICLR 2019 5 · Yifei HUANG, Yuan YAO, Weizhi Zhu

A belief persists long in machine learning that enlargement of margins over training data accounts for the resistance of models to overfitting by increasing the robustness. Yet Breiman shows a dilemma (Breiman, 1999) tha…

Generalization Bounds