Low-Cost Learning via Active Data Procurement

TL;DR

This paper introduces mechanisms for actively procuring data from strategic agents under budget constraints, providing guarantees on predictive error that improve with increased budget and leveraging data-cost correlations.

Contribution

It develops a framework converting no-regret algorithms into active data procurement mechanisms with robust risk bounds under strategic behavior and budget limits.

Findings

Achieves risk bounds of order 1/√B with budget B.

Provides regret bounds of order T/√B for the procurement process.

Demonstrates lower bounds matching the regret bounds.

Abstract

We design mechanisms for online procurement of data held by strategic agents for machine learning tasks. The challenge is to use past data to actively price future data and give learning guarantees even when an agent's cost for revealing her data may depend arbitrarily on the data itself. We achieve this goal by showing how to convert a large class of no-regret algorithms into online posted-price and learning mechanisms. Our results in a sense parallel classic sample complexity guarantees, but with the key resource being money rather than quantity of data: With a budget constraint $B$, we give robust risk (predictive error) bounds on the order of $1/\sqrt{B}$. Because we use an active approach, we can often guarantee to do significantly better by leveraging correlations between costs and data. Our algorithms and analysis go through a model of no-regret learning with $T$ arriving pairs (cost, data) and a budget constraint of $B$. Our regret bounds for this model are on the order of $T/\sqrt{B}$ and we give lower bounds on the same order.