The Missing Margin: How Sample Corruption Affects Distance to the Boundary in ANNs

14 February 2023

Papers citing "The Missing Margin: How Sample Corruption Affects Distance to the Boundary in ANNs"

8 / 8 papers shown

Title
Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective Gowthami Somepalli Liam H. Fowl Arpit Bansal Ping Yeh-Chiang Yehuda Dar Richard Baraniuk Micah Goldblum Tom Goldstein 50 67 0 15 Mar 2022
Representation Based Complexity Measures for Predicting Generalization in Deep Learning Parth Natekar Manik Sharma 44 36 0 04 Dec 2020
Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision Boundary Shuyue Guan Murray H. Loew 83 28 0 16 Sep 2020
Characterizing the Decision Boundary of Deep Neural Networks Hamid Karimi Hanyu Wang Jiliang Tang 58 67 0 24 Dec 2019
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks Kaifeng Lyu Jian Li 89 336 0 13 Jun 2019
Predicting the Generalization Gap in Deep Networks with Margin Distributions Yiding Jiang Dilip Krishnan H. Mobahi Samy Bengio UQCV 95 199 0 28 Sep 2018
DeepFool: a simple and accurate method to fool deep neural networks Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi P. Frossard AAML 154 4,905 0 14 Nov 2015
Deep Learning and the Information Bottleneck Principle Naftali Tishby Noga Zaslavsky DRL 214 1,592 0 09 Mar 2015