Automated Mechanism Design for Classification with Partial Verification

by   Hanrui Zhang, et al.

We study the problem of automated mechanism design with partial verification, where each type can (mis)report only a restricted set of types (rather than any other type), induced by the principal's limited verification power. We prove hardness results when the revelation principle does not necessarily hold, as well as when types have even minimally different preferences. In light of these hardness results, we focus on truthful mechanisms in the setting where all types share the same preference over outcomes, which is motivated by applications in, e.g., strategic classification. We present a number of algorithmic and structural results, including an efficient algorithm for finding optimal deterministic truthful mechanisms, which also implies a faster algorithm for finding optimal randomized truthful mechanisms via a characterization based on convexity. We then consider a more general setting, where the principal's cost is a function of the combination of outcomes assigned to each type. In particular, we focus on the case where the cost function is submodular, and give generalizations of essentially all our results in the classical setting where the cost function is additive. Our results provide a relatively complete picture for automated mechanism design with partial verification.


page 1

page 2

page 3

page 4


Automated Dynamic Mechanism Design

We study Bayesian automated mechanism design in unstructured dynamic env...

Probabilistic Verification in Mechanism Design

We introduce a model of probabilistic verification in a mechanism design...

Optimal Deterministic Mechanisms for an Additive Buyer

We study revenue maximization by deterministic mechanisms for the simple...

Mechanism Design for Multi-Party Machine Learning

In a multi-party machine learning system, different parties cooperate on...

Complexity of Mechanism Design

The aggregation of conflicting preferences is a central problem in multi...

Partial Verification as a Substitute for Money

Recent work shows that we can use partial verification instead of money ...

Delegated Stochastic Probing

Delegation covers a broad class of problems in which a principal doesn't...