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...
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...
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to co...
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...