most citedPILLAR: How to make semi-private learning more effective

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Atmospheric Transport Modeling of CO with Neural Networks

Vitus Benson, Ana Bastos, Christian Reimers +3

Accurately describing the distribution of CO in the atmosphere with atmospheric tracer transport models is essential for greenhouse gas monitoring and verification support syst…

cs.LG2024

Strong Copyright Protection for Language Models via Adaptive Model Fusion

Javier Abad, Konstantin Donhauser, Francesco Pinto +1

The risk of language models unintentionally reproducing copyrighted material from their training data has led to the development of various protective measures. In this paper, we p…

cs.LG2023

How robust accuracy suffers from certified training with convex relaxations

Piersilvio De Bartolomeis, Jacob Clarysse, Amartya Sanyal +1

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: e…

cs.LG20231 cited

PILLAR: How to make semi-private learning more effective

Francesco Pinto, Yaxi Hu, Fanny Yang +1

In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that, un…

stat.ML2023

Strong inductive biases provably prevent harmless interpolation

Michael Aerni, Marco Milanta, Konstantin Donhauser +1

Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization. In contrast, modern overparameterized models can yield small test error despite…

stat.ML2023

Tight bounds for maximum -margin classifiers

Stefan Stojanovic, Konstantin Donhauser, Fanny Yang

Popular iterative algorithms such as boosting methods and coordinate descent on linear models converge to the maximum -margin classifier, a.k.a. sparse hard-margin SVM, in…