134 citations · 330 across the 35 of their papers we have counts for
5 papers · 1 filter
Margin-based sampling in high dimensions: When being active is less efficient than staying passive
Alexandru Tifrea, Jacob Clarysse, Fanny Yang
It is widely believed that given the same labeling budget, active learning (AL) algorithms like margin-based active learning achieve better predictive performance than passive lear…
How unfair is private learning ?
Amartya Sanyal, Yaxi Hu, Fanny Yang
As machine learning algorithms are deployed on sensitive data in critical decision making processes, it is becoming increasingly important that they are also private and fair. In t…
Provable concept learning for interpretable predictions using variational autoencoders
Armeen Taeb, Nicolo Ruggeri, Carina Schnuck +1
In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available. Many attempts to provide such explanations r…
Why adversarial training can hurt robust accuracy
Jacob Clarysse, Julia Hörrmann, Fanny Yang
Machine learning classifiers with high test accuracy often perform poorly under adversarial attacks. It is commonly believed that adversarial training alleviates this issue. In thi…
Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias
Konstantin Donhauser, Nicolo Ruggeri, Stefan Stojanovic +1
Good generalization performance on high-dimensional data crucially hinges on a simple structure of the ground truth and a corresponding strong inductive bias of the estimator. Even…