English

Notes on Margin Training and Margin p-Values for Deep Neural Network Classifiers

Machine Learning 2019-12-06 v2 Machine Learning
Authors: George Kesidis , David J. Miller , Zhen Xiang
View on arXiv ↗ PDF ↗

Abstract

We provide a new local class-purity theorem for Lipschitz continuous DNN classifiers. In addition, we discuss how to achieve classification margin for training samples. Finally, we describe how to compute margin p-values for test samples.

Cite

@article{arxiv.1910.08032,
  title  = {Notes on Margin Training and Margin p-Values for Deep Neural Network Classifiers},
  author = {George Kesidis and David J. Miller and Zhen Xiang},
  journal= {arXiv preprint arXiv:1910.08032},
  year   = {2019}
}

Related papers

View all related →
Computer Vision and Pattern Recognition · Computer Science
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama
2018-11-02
Machine Learning · Computer Science
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
Mahyar Fazlyab, Alexander Robey, Hamed Hassani, Manfred Morari +1
2023-01-18
Machine Learning · Computer Science
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
Mahyar Fazlyab, Taha Entesari, Aniket Roy, Rama Chellappa
2025-03-27
Machine Learning · Computer Science
DP-SGD Without Clipping: The Lipschitz Neural Network Way
Louis Bethune, Thomas Massena, Thibaut Boissin, Yannick Prudent +5
2024-02-23
Machine Learning · Statistics
Large Margin Deep Networks for Classification
Gamaleldin F. Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan +1
2018-12-05
Machine Learning · Computer Science
Recent Advances in Large Margin Learning
Yiwen Guo, Changshui Zhang
2021-06-22
Machine Learning · Computer Science
LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence
Rahul Yedida, Snehanshu Saha, Tejas Prashanth
2020-08-04
Machine Learning · Statistics
Local Lipschitz Bounds of Deep Neural Networks
Calypso Herrera, Florian Krach, Josef Teichmann
2023-02-10
Machine Learning · Computer Science
Metric Learning via Maximizing the Lipschitz Margin Ratio
Mingzhi Dong, Xiaochen Yang, Yang Wu, Jing-Hao Xue
2018-02-13
Computer Vision and Pattern Recognition · Computer Science
P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
Wei Hu, QiHao Zhao, Yangyu Huang, Fan Zhang
2020-09-16
Computation and Language · Computer Science
Large Margin Neural Language Model
Jiaji Huang, Yi Li, Wei Ping, Liang Huang
2018-08-29
Machine Learning · Computer Science
Margin-Based Regularization and Selective Sampling in Deep Neural Networks
Berry Weinstein, Shai Fine, Yacov Hel-Or
2020-09-15
Machine Learning · Computer Science
Spectrally-normalized margin bounds for neural networks
Peter Bartlett, Dylan J. Foster, Matus Telgarsky
2017-12-06
Machine Learning · Computer Science
LipBaB: Computing exact Lipschitz constant of ReLU networks
Aritra Bhowmick, Meenakshi D'Souza, G. Srinivasa Raghavan
2021-07-07
Machine Learning · Computer Science
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen
2024-03-19
Machine Learning · Computer Science
The Missing Margin: How Sample Corruption Affects Distance to the Boundary in ANNs
Marthinus W. Theunissen, Coenraad Mouton, Marelie H. Davel
2023-02-15
Machine Learning · Computer Science
Computable Lipschitz Bounds for Deep Neural Networks
Moreno Pintore, Bruno Després
2024-10-29
Machine Learning · Computer Science
On Tighter Generalization Bound for Deep Neural Networks: CNNs, ResNets, and Beyond
Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt +1
2019-07-05
Machine Learning · Statistics
Predicting the Generalization Gap in Deep Networks with Margin Distributions
Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio
2019-06-13
Machine Learning · Statistics
Regularisation of Neural Networks by Enforcing Lipschitz Continuity
Henry Gouk, Eibe Frank, Bernhard Pfahringer, Michael J. Cree
2020-08-11
Machine Learning · Computer Science
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif
2020-11-10
Machine Learning · Computer Science
CLIP: Cheap Lipschitz Training of Neural Networks
Leon Bungert, René Raab, Tim Roith, Leo Schwinn +1
2022-11-02
Statistics Theory · Mathematics
On deviation probabilities in non-parametric regression with heavy-tailed noise
Anna Ben-Hamou, Arnaud Guyader
2024-12-02
Machine Learning · Computer Science
Lipschitz Properties for Deep Convolutional Networks
Radu Balan, Maneesh Singh, Dongmian Zou
2017-01-20
Machine Learning · Statistics
Large dimensional analysis of general margin based classification methods
Hanwen Huang, Qinglong Yang
2021-10-19
R2 v1 2026-06-23T11:46:59.610Z