Channel coding perspective of recommendation systems
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
Channel coding perspective of recommendation systems
|
|
Creator |
ADITYA, ST
DABEER, O DEY, BK |
|
Description |
Motivated by recommendation systems, we consider the problem of estimating block constant binary matrices (of size m x n) from sparse and noisy observations. The observations are obtained from the underlying block constant matrix after unknown row and column permutations, erasures, and errors. We derive upper and lower bounds on the achievable probability of error. For fixed erasure and error probability, we show that there exists a constant C(1) such that if the cluster sizes are less than C(1) In(mn), then for any algorithm the probability of error approaches one as m,n -> 77 infinity. On the other hand, we show that a simple polynomial time algorithm gives probability of error diminishing to zero provided the cluster sizes are greater than C(2) In(mn) for a suitable constant C(2).
|
|
Publisher |
IEEE
|
|
Date |
2011-10-25T00:01:39Z
2011-12-15T09:11:50Z 2011-10-25T00:01:39Z 2011-12-15T09:11:50Z 2009 |
|
Type |
Proceedings Paper
|
|
Identifier |
2009 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, VOLS 1- 4,319-323
978-1-4244-4312-3 http://dx.doi.org/10.1109/ISIT.2009.5205549 http://dspace.library.iitb.ac.in/xmlui/handle/10054/15548 http://hdl.handle.net/100/2318 |
|
Source |
IEEE International Symposium on Information Theory (ISIT 2009),Seoul, SOUTH KOREA,JUN 28-JUL 03, 2009
|
|
Language |
English
|
|