# On the Capacity of Information Processing Systems

2 DYOGENE - Dynamics of Geometric Networks
Inria de Paris, CNRS - Centre National de la Recherche Scientifique : UMR 8548, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : We propose and analyze a family of information processing systems, where a finite set of experts or servers are employed to extract information about a stream of incoming jobs. Each job is associated with a hidden label drawn from some prior distribution. An inspection by an expert produces a noisy outcome that depends both on the job’s hidden label and the type of the expert and occupies the expert for a finite time duration. A decision-maker’s task is to dynamically assign inspections so that the resulting out-comes can be used to accurately recover the labels of all jobs, while keeping the system stable. Among our chief motivations are applications in crowd sourcing, diagnostics, and experiment designs, where one wishes to efficiently learn the nature of a large number of items, using a finite pool of computational resources or human agents. We focus on the capacity of such an information processing system. Given a level of accuracy guarantee, we ask how many experts are needed in order to stabilize the system, and through what inspection architecture. Our main result provides an adaptive inspection policy that is asymptotically optimal in the following sense: the ratio between the required number of experts under our policy and the theoretical optimal converges to one, as the probability of error in label recovery, $δ$ , tends to zero.
Keywords :
Document type :
Journal articles
Domain :

https://hal.archives-ouvertes.fr/hal-01940447
Contributor : Laurent Massoulié <>
Submitted on : Friday, November 30, 2018 - 11:51:57 AM
Last modification on : Thursday, July 1, 2021 - 5:58:08 PM

### Identifiers

• HAL Id : hal-01940447, version 1

### Citation

Laurent Massoulié, Kuang Xu. On the Capacity of Information Processing Systems. Operations Research, INFORMS, 2018, 66 (2), pp.568-586. ⟨hal-01940447⟩

Record views