Private graphon estimation via sum-of-squares

arXiv:2403.12213v1 Announce Type: cross
Abstract: We develop the first pure node-differentially-private algorithms for learning stochastic block models and for graphon estimation with polynomial running time for any constant number of blocks. The statistical utility guarantees match those of the previous best information-theoretic (exponential-time) node-private mechanisms for these problems. The algorithm is based on an exponential mechanism for a score function defined in terms of a sum-of-squares relaxation whose level depends on the number of blocks. The key ingredients of our …

abstract algorithm algorithms arxiv block cs.cc cs.ds cs.lg information match node polynomial running squares statistical stat.ml stochastic the algorithm type utility via