Christoph H. Lampert

Towards Practical Conditional Risk Minimization.

2018 · arXiv (Cornell University)

We study conditional risk minimization (CRM), i.e. the problem of learning a hypothesis of minimal risk for prediction at the next step of a sequentially arriving dependent data. Despite it being a fundamental problem, successful …

1-Lipschitz Neural Networks are more expressive with N-Activations

2023 · arXiv (Cornell University)

A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs. Mathematically, this means one strives …

Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions

2025 · arXiv (Cornell University)

Personalized federated learning has emerged as a popular approach to training on devices holding statistically heterogeneous data, known as clients. However, most existing approaches require a client to have labeled data for training or finetuning …