On Robustness Properties of Convex Risk Minimization Methods for Pattern Recognition

By Andreas Christmann, Ingo Steinwart. 2004

150 citations recorded by the source corpus.

Subfields: Computational Mechanics, Statistics and Probability, Safety, Robustness & Interpretability, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Shie Mannor
2. Huan Xu
3. Constantine Caramanis
4. J. Paul Brooks
5. Battista Biggio
6. Fabio Roli
7. Pavel Laskov
8. Blaine Nelson

In Statistics and Probability

1. Huan Xu
2. Shie Mannor
3. Constantine Caramanis
4. Marco Barreno
5. J. Paul Brooks
6. Battista Biggio
7. Anthony D. Joseph
8. Fabio Roli

In Safety, Robustness & Interpretability

1. Battista Biggio
2. Fabio Roli
3. Giorgio Giacinto
4. Giorgio Fumera
5. Davide Maiorca
6. Nicolas Papernot
7. Blaine Nelson
8. Patrick Drew McDaniel

In Statistical Learning Theory

1. Battista Biggio
2. Fabio Roli
3. Pavel Laskov
4. Blaine Nelson
5. Shie Mannor
6. Giorgio Fumera
7. Huan Xu
8. Constantine Caramanis

Citations in the corpus

• The security of machine learning (2010, background): “Christmann and Steinwart (2004) study robustness for a general family of learning methods.”
• Security Evaluation of Support Vector Machines in Adversarial Environments (2014, background): “and theoretically, since such losses are designed to limit the impact of any single (attack) point on the resulting learned function. This has been also studied from a more theoretical perspective in [23], exploiting the framework of Robust Statistics [35, 50]. A similar effect is obtained by using ”
• Support vector machines under adversarial label contamination (2015, background): “Robust statistics have also been exploited to formally show that the influence function of SVM-like algorithms can be bounded under certain conditions [30]; e.”
• Robustness and Regularization of Support Vector Machines (2008, methodology): “Based on this notion of robustness, Christmann and Steinwart (2004) showed that many kernel classification algorithms, including SVM, are robust in the sense of having a finite Influence Function.”
• Support Vector Machines with the Ramp Loss and the Hard Margin Loss (2011, background): “Along these lines, Christmann and Steinwart (2004) investigate the robustness properties of SVM with the linear and Gaussian kernels as an application of a more general theory of robustness.”
• Behavior of Machine Learning Algorithms in Adversarial Environments (2010, background): “Christmann and Steinwart [2004] study robustness for a general family of learning methods.”
• Pattern Recognition Systems under Attack: Design Issues and Research Challenges (2014, background): “Notably, in [27] the robustness of SVMs to training data contamination has been formally analyzed under the framework of Robust Statistics [40, 53], highlighting that bounded kernels and bounded loss functions may significantly limit the outliers’ impact on classifier training.”
• Support Vector Machines Under Adversarial Label Noise (2011, methodology): “The robustness issues of margin-based learning methods have been studied by Christmann and Steinwart (2004).”