LATIDIA · Ciberseguridad

Aprendizaje fiable en entornos desafiantes

arXiv:2304.03370v3 Announce Type: replace-cross Abstract: El problema de diseñar estudiantes que garanticen que sus predicciones sean probablemente correctas es de creciente importancia en el aprendizaje automático. Sin embargo, le

La noticia

arXiv:2304.03370v3 Announce Type: replace-cross Abstract: The problem of designing learners that provide guarantees that their predictions are provably correct is of increasing importance in machine learning. However, learning theoretic guarantees have only been considered in very specific settings. In this work, we consider the design and analysis of reliable learners in challenging test-time environments as encountered in modern machine learning problems: namely `adversarial' test-time attacks (in several variations) and `natural' distribution shifts. In this work, we provide a reliable learner with provably optimal guarantees in such settings. We discuss practical implementations of the learner and further show that our algorithm achieves strong positive performance guarantees on several natural examples: for