Sciweavers

236 search results - page 5 / 48
» Bias and Variance Approximation in Value Function Estimates
Sort
View
STOC
2004
ACM
110views Algorithms» more  STOC 2004»
14 years 7 months ago
On sums of independent random variables with unbounded variance, and estimating the average degree in a graph
We prove the following inequality: for every positive integer n and every collection X1, . . . , Xn of nonnegative independent random variables that each has expectation 1, the pr...
Uriel Feige
ICML
1999
IEEE
14 years 8 months ago
Approximation Via Value Unification
: Numerical function approximation over a Boolean domain is a classical problem with wide application to data modeling tasks and various forms of learning. A great many function ap...
Paul E. Utgoff, David J. Stracuzzi
TSP
2010
13 years 2 months ago
Performance of instantaneous frequency rate estimation using high-order phase function
Abstract--The high-order phase function (HPF) is a useful tool to estimate the instantaneous frequency rate (IFR) of a signal with a polynomial phase. In this paper, the asymptotic...
Pu Wang, Hongbin Li, Igor Djurovic, Braham Himed
AUSAI
2003
Springer
13 years 11 months ago
On Why Discretization Works for Naive-Bayes Classifiers
We investigate why discretization is effective in naive-Bayes learning. We prove a theorem that identifies particular conditions under which discretization will result in naiveBay...
Ying Yang, Geoffrey I. Webb
AAAI
2012
11 years 9 months ago
Generalized Sampling and Variance in Counterfactual Regret Minimization
In large extensive form games with imperfect information, Counterfactual Regret Minimization (CFR) is a popular, iterative algorithm for computing approximate Nash equilibria. Whi...
Richard G. Gibson, Marc Lanctot, Neil Burch, Duane...