Skip to yearly menu bar Skip to main content


Delegating Data Collection in Decentralized Machine Learning

Nivasini Ananthakrishnan · Stephen Bates · Michael Jordan · Nika Haghtalab

MR1 & MR2 - Number 78
[ ]
Fri 3 May 8 a.m. PDT — 8:30 a.m. PDT

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 that achieve $1-1/\epsilon$ fraction of the optimal utility. To address the lack of a priori knowledge regarding the optimal performance, we give a convex program that can adaptively and efficiently compute the optimal contract. We also analyze the optimal utility and linear contracts for the more complex setting of multiple interactions.

Live content is unavailable. Log in and register to view live content