6 citations · 20 across the 9 of their papers we have counts for
8 papers · 1 filter
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
Andrew Engel, Zhichao Wang, Natalie S. Frank +4
A recent trend in explainable AI research has focused on surrogate modeling, where neural networks are approximated as simpler ML algorithms such as kernel machines. A second trend…
The Adversarial Consistency of Surrogate Risks for Binary Classification
Natalie Frank, Jonathan Niles-Weed
We study the consistency of surrogate risks for robust binary classification. It is common to learn robust classifiers by adversarial training, which seeks to minimize the expected…
The Consistency of Adversarial Training for Binary Classification
Natalie S. Frank, Jonathan Niles-Weed
Robustness to adversarial perturbations is of paramount concern in modern machine learning. One of the state-of-the-art methods for training robust classifiers is adversarial train…
Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification
Natalie S. Frank, Jonathan Niles-Weed
Adversarial training is one of the most popular methods for training methods robust to adversarial attacks, however, it is not well-understood from a theoretical perspective. We pr…
On the Existence of the Adversarial Bayes Classifier (Extended Version)
Pranjal Awasthi, Natalie S. Frank, Mehryar Mohri
Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many import…
Calibration and Consistency of Adversarial Surrogate Losses
Pranjal Awasthi, Natalie Frank, Anqi Mao +2
Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the…
On the Rademacher Complexity of Linear Hypothesis Sets
Pranjal Awasthi, Natalie Frank, Mehryar Mohri
Linear predictors form a rich class of hypotheses used in a variety of learning algorithms. We present a tight analysis of the empirical Rademacher complexity of the family of line…
Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks
Pranjal Awasthi, Natalie Frank, Mehryar Mohri
Adversarial or test time robustness measures the susceptibility of a classifier to perturbations to the test input. While there has been a flurry of recent work on designing defens…