Delegating Data Collection in Decentralized Machine Learning

arXiv:2309.01837v2 Announce Type: replace
Abstract: Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two fundamental information asymmetries that arise in decentralized ML: uncertainty in the assessment of model quality and uncertainty regarding the optimal performance of any model. We show that a principal can cope with such asymmetry via simple linear contracts …

abstract arxiv collection cs.lg data data collection deal decentralized design ecosystems emergence fundamental information machine machine learning near stat.ml study theory type uncertainty