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»
15 years 9 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
15 years 10 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
14 years 4 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
15 years 1 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
84
Voted
AAAI
2012
12 years 11 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...