Surprising Failures of Standard Practices in ML When the Sample Size Is Small
24.03.2023 11:15 – 12:15
RESEARCH CENTER FOR STATISTICS SEMINAR / ABSTRACT
In this talk, we discuss two failure cases of common practices that are typically believed to improve on vanilla methods: (i) adversarial training can lead to worse robust accuracy than standard training (ii) active learning can lead to a worse classifier than a model trained using uniform samples. In particular, we can prove both mathematically and empirically, that such failures can happen in the small-sample regime. We discuss high-level explanations derived from the theory, that shed light on the causes of these phenomena in practice.
Lieu
Bâtiment: Uni Mail
ONLINE & in Uni Mail
Boulevard du Pont-d'Arve 40
1205 Geneva
Room M 3393, 3rd floor
Organisé par
Faculté d'économie et de managementResearch Center for Statistics
Intervenant-e-s
Fanny YANG, ETH Zurich, Switzerlandentrée libre
Classement
Catégorie: Séminaire