Sciweavers

152 search results - page 1 / 31
» {Algorithmic Minimal Sufficient Statistics: a New Definition
Sort
View
ECCC
2010
107views more  ECCC 2010»
13 years 4 months ago
{Algorithmic Minimal Sufficient Statistics: a New Definition
We express some criticism about the definition of an algorithmic sufficient statistic and, in particular, of an algorithmic minimal sufficient statistic. We propose another defini...
Nikolay K. Vereshchagin
CIE
2009
Springer
13 years 8 months ago
Algorithmic Minimal Sufficient Statistic Revisited
Abstract. We express some criticism about the definition of an algorithmic sufficient statistic and, in particular, of an algorithmic minimal sufficient statistic. We propose anoth...
Nikolay K. Vereshchagin
KDD
1998
ACM
99views Data Mining» more  KDD 1998»
13 years 8 months ago
On the Efficient Gathering of Sufficient Statistics for Classification from Large SQL Databases
For a wide variety of classification algorithms, scalability to large databases can be achieved by observing that most algorithms are driven by a set of sufficient statistics that...
Goetz Graefe, Usama M. Fayyad, Surajit Chaudhuri
CORR
2000
Springer
116views Education» more  CORR 2000»
13 years 4 months ago
Algorithmic Statistics
While Kolmogorov complexity is the accepted absolute measure of information content of an individual finite object, a similarly absolute notion is needed for the relation between a...
Péter Gács, John Tromp, Paul M. B. V...
DAC
2005
ACM
14 years 5 months ago
An efficient algorithm for statistical minimization of total power under timing yield constraints
Power minimization under variability is formulated as a rigorous statistical robust optimization program with a guarantee of power and timing yields. Both power and timing metrics...
Murari Mani, Anirudh Devgan, Michael Orshansky