@inproceedings{fe88c0665d774ae9861cf457e3901686,

title = "Simultaneous private learning of multiple concepts",

abstract = "We investigate the direct-sum problem in the context of differentially private PAC learning: What is the sample complexity of solving k learning tasks simultaneously under differential privacy, and how does this cost compare to that of solving k learning tasks without privacy? In our setting, an individual example consists of a domain element x labeled by k unknown concepts (c1; ck). The goal of a multi-learner is to output k hypotheses (h1; hk) that generalize the input examples. Without concern for privacy, the sample complexity needed to simultaneously learn k concepts is essentially the same as needed for learning a single concept. Under differential privacy, the basic strategy of learning each hypothesis independently yields sample complexity that grows polynomially with k. For some concept classes, we give multi-learners that require fewer samples than the basic strategy. Unfortunately, however, we also give lower bounds showing that even for very simple concept classes, the sample cost of private multi-learning must grow polynomially in k.",

keywords = "Agnostic learning, Differential privacy, Directsum, PAC learning",

author = "Mark Bun and Kobbi Nissim and Uri Stemmer",

year = "2016",

month = jan,

day = "14",

doi = "https://doi.org/10.1145/2840728.2840747",

language = "الإنجليزيّة",

series = "ITCS 2016 - Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science",

pages = "369--380",

booktitle = "ITCS 2016 - Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science",

note = "7th ACM Conference on Innovations in Theoretical Computer Science, ITCS 2016 ; Conference date: 14-01-2016 Through 16-01-2016",

}