Sciweavers

126 search results - page 1 / 26
» Improved Approximation of Linear Threshold Functions
Sort
View
COCO
2009
Springer
106views Algorithms» more  COCO 2009»
13 years 11 months ago
Improved Approximation of Linear Threshold Functions
We prove two main results on how arbitrary linear threshold functions f(x) = sign(w · x − θ) over the n-dimensional Boolean hypercube can be approximated by simple threshold f...
Ilias Diakonikolas, Rocco A. Servedio
STOC
2012
ACM
209views Algorithms» more  STOC 2012»
11 years 7 months ago
Nearly optimal solutions for the chow parameters problem and low-weight approximation of halfspaces
The Chow parameters of a Boolean function f : {−1, 1}n → {−1, 1} are its n + 1 degree-0 and degree-1 Fourier coefficients. It has been known since 1961 [Cho61, Tan61] that ...
Anindya De, Ilias Diakonikolas, Vitaly Feldman, Ro...
ICML
2007
IEEE
14 years 5 months ago
Tracking value function dynamics to improve reinforcement learning with piecewise linear function approximation
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to co...
Chee Wee Phua, Robert Fitch
STOC
2009
ACM
119views Algorithms» more  STOC 2009»
14 years 5 months ago
Explicit construction of a small epsilon-net for linear threshold functions
We give explicit constructions of epsilon nets for linear threshold functions on the binary cube and on the unit sphere. The size of the constructed nets is polynomial in the dime...
Yuval Rabani, Amir Shpilka