Aritz Pérez

Minimax Classification with 0-1 Loss and Performance Guarantees

2020 · arXiv (Cornell University)

Supervised classification techniques use training samples to find classification rules with small expected 0-1 loss. Conventional methods achieve efficient learning and out-of-sample generalization by minimizing surrogate losses over specific families of rules. This paper presents …

On the relative value of weak information of supervision for learning generative models: An empirical study

2022 · International Journal of Approximate Reasoning

Weakly supervised learning is aimed to learn predictive models from partially supervised data, an easy-to-collect alternative to the costly standard full supervision. During the last decade, the research community has striven to show that learning …

Decentralized Federated Learning of Probabilistic Generative Classifiers

2025 · arXiv (Cornell University)

Federated learning is a paradigm of increasing relevance in real world applications, aimed at building a global model across a network of heterogeneous users without requiring the sharing of private data. We focus on model …