Private PAC Learning May be Harder than Online Learning

arXiv:2402.11119v1 Announce Type: cross
Abstract: We continue the study of the computational complexity of differentially private PAC learning and how it is situated within the foundations of machine learning. A recent line of work uncovered a qualitative equivalence between the private PAC model and Littlestone's mistake-bounded model of online learning, in particular, showing that any concept class of Littlestone dimension $d$ can be privately PAC learned using $\mathrm{poly}(d)$ samples. This raises the natural question of whether there might be a …

arxiv complexity computational continue cs.cr cs.ds cs.lg foundations machine machine learning may mistake online learning pac private qualitative study uncovered work