On Robustness and Regularization of Structural Support Vector Machines

By MohamadAli Torkamani, Daniel Lowd. 2014

21 citations recorded by the source corpus.

Subfields: 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 Safety, Robustness & Interpretability

1. Aleksander Madry
2. Dimitris Tsipras
3. Nicholas Carlini
4. Alexander Turner
5. Logan Engstrom
6. Battista Biggio
7. Fabio Roli
8. Matthias Hein

In Statistical Learning Theory

1. Battista Biggio
2. Fabio Roli
3. Aleksander Madry
4. Dimitris Tsipras
5. Shibani Santurkar

Citations in the corpus

• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, methodology): “…learning problems and robust optimization, which has in turn enabled approximating computationally-demanding secure learning models (e.g., game-theoretical ones) with more e ffi cient ones based on regularizing the objective function in a specific manner [46, 71, 72], also in structured learning [89].”
• Robustness May Be at Odds with Accuracy (2018, background): “A key implication of this view is that adversarial training should be beneficial for the standard accuracy of a model (Torkamani & Lowd, 2013, 2014; Goodfellow et al., 2014b; Miyato et al., 2018).”