# Budget Feasible Mechanisms for Experimental Design

arXiv: https://arxiv.org/abs/1302.5724 · HTML: https://mlsanity.com/paper/1302.5724/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2013.

## Built on by (most cited first, 1 of 1)

- [Information Discrepancy in Strategic Learning](https://mlsanity.com/paper/2103.01028/) (2021)

## Abstract (arXiv)

In the classical experimental design setting, an experimenter E has access to a population of n potential experiment subjects i∈ 1,...,n, each associated with a vector of features xi∈ Rd. Conducting an experiment with subject i reveals an unknown value yi∈ R to E. E typically assumes some hypothetical relationship between xi's and yi's, e.g., yi ≈ β xi, and estimates β from experiments, e.g., through linear regression. As a proxy for various practical constraints, E may select only a subset of subjects on which to conduct the experiment. We initiate the study of budgeted mechanisms for experimental design. In this setting, E has a budget B. Each subject i declares an associated cost ci >0 to be part of the experiment, and must be paid at least her cost. In particular, the Experimental Design Problem (EDP) is to find a set S of subjects for the experiment that maximizes V(S) = logdet(Id+sumi∈ SxiTxi) under the constraint sumi∈ Sci≤ B; our objective function corresponds to the information gain in parameter β that is learned through linear regression methods, and is related to the so-called D-optimality criterion. Further, the subjects are strategic and may lie about their costs. We present a deterministic, polynomial time, budget feasible mechanism scheme, that is approximately truthful and yields a constant factor approximation to EDP. In particular, for any small δ > 0 and ε > 0, we can construct a (12.98, ε)-approximate mechanism that is δ-truthful and runs in polynomial time in both n and loglogfracBεδ. We also establish that no truthful, budget-feasible algorithms is possible within a factor 2 approximation, and show how to generalize our approach to a wide class of learning problems, beyond linear regression.