DocumentCode :
2454566
Title :
On the complexity of statistical reasoning
Author :
Kilian, Joe ; Naor, Moni
Author_Institution :
NEC Res. Inst., Princeton, NJ, USA
fYear :
1995
fDate :
4-6 Jan 1995
Firstpage :
209
Lastpage :
217
Abstract :
We show that basic problems in reasoning about statistics are NP-hard to even approximately solve. We consider the problem of detecting internal inconsistencies in a set of statistics. We say that a set of statistics is ε-inconsistent if one of the probabilities must be off by at least ε. For a positive constant ε, we show NP-hard to distinguish ε-inconsistent statistics from self-consistent statistics. This result holds when restricted to complete sets of pairwise statistics over Boolean domains. We next consider what may, be determined about distributions with a given (consistent) set of pairwise statistics over Boolean domains. We show it NP-hard to distinguish between the case that Pr(Xi∧Xj) is necessarily 0 and the case that Pr(Xi∧Xj) can have any value in [0, ½]. Similarly, we show it NP-hard to distinguish between the case that |Corr(Xi, Xj)|=-1 and the case that |Corr(Xi , Xj)| is unconstrained. Whereas the connection between PCP and hardness of approximations has been known since Feige et al. (1991), we introduce the application of “zero-knowledge” PCP´s as a tool for proving NP-hardness results for approximation problems
Keywords :
computational complexity; inference mechanisms; probability; statistical analysis; Boolean domains; NP-hardness; approximation problems; inconsistent statistics; internal inconsistencies; pairwise statistics; self-consistent statistics; statistical reasoning complexity; Application software; Career development; Computer science; Mathematics; Statistical distributions; Statistics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Theory of Computing and Systems, 1995. Proceedings., Third Israel Symposium on the
Conference_Location :
Tel Aviv
Print_ISBN :
0-8186-6915-2
Type :
conf
DOI :
10.1109/ISTCS.1995.377030
Filename :
377030
Link To Document :
بازگشت