Skip navigation
Skip navigation

Convergence Analysis of Prediction Markets via Randomized Subspace Descent

Frongillo, Rafael; Reid, Mark

Description

Prediction markets are economic mechanisms for aggregating information about future events through sequential interactions with traders. The pricing mechanisms in these markets are known to be related to optimization algorithms in machine learning and through these connections we have some understanding of how equilibrium market prices relate to the beliefs of the traders in a market. However, little is known about rates and guarantees for the convergence of these sequential mechanisms, and two...[Show more]

dc.contributor.authorFrongillo, Rafael
dc.contributor.authorReid, Mark
dc.coverage.spatialMontreal, Canada
dc.date.accessioned2016-06-14T23:21:18Z
dc.date.createdDecember 7-12, 2015
dc.identifier.isbn9781510800410
dc.identifier.urihttp://hdl.handle.net/1885/103835
dc.description.abstractPrediction markets are economic mechanisms for aggregating information about future events through sequential interactions with traders. The pricing mechanisms in these markets are known to be related to optimization algorithms in machine learning and through these connections we have some understanding of how equilibrium market prices relate to the beliefs of the traders in a market. However, little is known about rates and guarantees for the convergence of these sequential mechanisms, and two recent papers cite this as an important open question. In this paper we show how some previously studied prediction market trading models can be understood as a natural generalization of randomized coordinate descent which we call randomized subspace descent (RSD). We establish convergence rates for RSD and leverage them to prove rates for the two prediction market models above, answering the open questions. Our results extend beyond standard centralized markets to arbitrary trade networks.
dc.publisherNeural Information Processing Systems Foundation
dc.relation.ispartofseries29th Conference on Neural Information Processing Systems NIPS 2015
dc.sourceReflection, Refraction and Hamiltonian Monte Carlo
dc.titleConvergence Analysis of Prediction Markets via Randomized Subspace Descent
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2015
local.identifier.absfor080603 - Conceptual Modelling
local.identifier.ariespublicationu4334215xPUB1598
local.type.statusPublished Version
local.contributor.affiliationFrongillo, Rafael, University of Colorado
local.contributor.affiliationReid, Mark, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.startpage1
local.bibliographicCitation.lastpage9
local.identifier.absseo970114 - Expanding Knowledge in Economics
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2016-06-14T09:04:12Z
local.identifier.scopusID2-s2.0-84965130386
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Frongillo_Convergence_Analysis_of_2015.pdf428.53 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator