Ugo Tanielian

Approximating Lipschitz continuous functions with GroupSort neural networks

2020 · arXiv (Cornell University)

Recent advances in adversarial attacks and Wasserstein GANs have advocated for use of neural networks with restricted Lipschitz constants. Motivated by these observations, we study the recently introduced GroupSort neural networks, with constraints on the …

Lessons from the AdKDD'21 Privacy-Preserving ML Challenge

2022 · arXiv (Cornell University)

Designing data sharing mechanisms providing performance and strong privacy guarantees is a hot topic for the Online Advertising industry. Namely, a prominent proposal discussed under the Improving Web Advertising Business Group at W3C only allows …