Timezone: »

Poster
Multiclass versus Binary Differentially Private PAC Learning
Satchit Sivakumar · Mark Bun · Marco Gaboardi

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
We show a generic reduction from multiclass differentially private PAC learning to binary private PAC learning. We apply this transformation to a recently proposed binary private PAC learner to obtain a private multiclass learner with sample complexity that has a polynomial dependence on the multiclass Littlestone dimension and a poly-logarithmic dependence on the number of classes. This yields a doubly exponential improvement in the dependence on both parameters over learners from previous work. Our proof extends the notion of $\Psi$-dimension defined in work of Ben-David et al. [JCSS, 1995] to the online setting and explores its general properties.