Cost-performance tradeoffs in unreliable computation architectures

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We investigate unreliable computation problem under cost and fidelity constraints. We introduce a framework, where we observe a noise-corrupted version of correct computation while incurring an associated cost. We consider several cost models formalizing the relationship between fidelity of an unreliable computation and its cost. We demonstrate that a single unreliable computation incurs less cost than a fusion of several less costly and less reliable computations while achieving same MSE performance under concave and linear costs. We show that fusing several less costly and less reliable computation yield a better cost-performance tradeoff than a single unreliable computation under convex costs.

Original languageEnglish (US)
Title of host publicationConference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages215-219
Number of pages5
ISBN (Electronic)9781538639542
DOIs
StatePublished - Mar 1 2017
Event50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States
Duration: Nov 6 2016Nov 9 2016

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Other

Other50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
CountryUnited States
CityPacific Grove
Period11/6/1611/9/16

Fingerprint

Costs
Fusion reactions

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Cite this

Donmez, M. A., Raginsky, M., Singer, A. C., & Varshney, L. R. (2017). Cost-performance tradeoffs in unreliable computation architectures. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 215-219). [7869027] (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869027

Cost-performance tradeoffs in unreliable computation architectures. / Donmez, Mehmet A.; Raginsky, Maxim; Singer, Andrew Carl; Varshney, Lav R.

Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. ed. / Michael B. Matthews. IEEE Computer Society, 2017. p. 215-219 7869027 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Donmez, MA, Raginsky, M, Singer, AC & Varshney, LR 2017, Cost-performance tradeoffs in unreliable computation architectures. in MB Matthews (ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869027, Conference Record - Asilomar Conference on Signals, Systems and Computers, IEEE Computer Society, pp. 215-219, 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, United States, 11/6/16. https://doi.org/10.1109/ACSSC.2016.7869027
Donmez MA, Raginsky M, Singer AC, Varshney LR. Cost-performance tradeoffs in unreliable computation architectures. In Matthews MB, editor, Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 215-219. 7869027. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2016.7869027
Donmez, Mehmet A. ; Raginsky, Maxim ; Singer, Andrew Carl ; Varshney, Lav R. / Cost-performance tradeoffs in unreliable computation architectures. Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. editor / Michael B. Matthews. IEEE Computer Society, 2017. pp. 215-219 (Conference Record - Asilomar Conference on Signals, Systems and Computers).
@inproceedings{46dcdb8e7c3c4c4abdd90b99ea89a4f8,
title = "Cost-performance tradeoffs in unreliable computation architectures",
abstract = "We investigate unreliable computation problem under cost and fidelity constraints. We introduce a framework, where we observe a noise-corrupted version of correct computation while incurring an associated cost. We consider several cost models formalizing the relationship between fidelity of an unreliable computation and its cost. We demonstrate that a single unreliable computation incurs less cost than a fusion of several less costly and less reliable computations while achieving same MSE performance under concave and linear costs. We show that fusing several less costly and less reliable computation yield a better cost-performance tradeoff than a single unreliable computation under convex costs.",
author = "Donmez, {Mehmet A.} and Maxim Raginsky and Singer, {Andrew Carl} and Varshney, {Lav R}",
year = "2017",
month = "3",
day = "1",
doi = "10.1109/ACSSC.2016.7869027",
language = "English (US)",
series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
pages = "215--219",
editor = "Matthews, {Michael B.}",
booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",

}

TY - GEN

T1 - Cost-performance tradeoffs in unreliable computation architectures

AU - Donmez, Mehmet A.

AU - Raginsky, Maxim

AU - Singer, Andrew Carl

AU - Varshney, Lav R

PY - 2017/3/1

Y1 - 2017/3/1

N2 - We investigate unreliable computation problem under cost and fidelity constraints. We introduce a framework, where we observe a noise-corrupted version of correct computation while incurring an associated cost. We consider several cost models formalizing the relationship between fidelity of an unreliable computation and its cost. We demonstrate that a single unreliable computation incurs less cost than a fusion of several less costly and less reliable computations while achieving same MSE performance under concave and linear costs. We show that fusing several less costly and less reliable computation yield a better cost-performance tradeoff than a single unreliable computation under convex costs.

AB - We investigate unreliable computation problem under cost and fidelity constraints. We introduce a framework, where we observe a noise-corrupted version of correct computation while incurring an associated cost. We consider several cost models formalizing the relationship between fidelity of an unreliable computation and its cost. We demonstrate that a single unreliable computation incurs less cost than a fusion of several less costly and less reliable computations while achieving same MSE performance under concave and linear costs. We show that fusing several less costly and less reliable computation yield a better cost-performance tradeoff than a single unreliable computation under convex costs.

UR - http://www.scopus.com/inward/record.url?scp=85016328712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016328712&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2016.7869027

DO - 10.1109/ACSSC.2016.7869027

M3 - Conference contribution

AN - SCOPUS:85016328712

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 215

EP - 219

BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

A2 - Matthews, Michael B.

PB - IEEE Computer Society

ER -