Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.jmateco.2007.04.006
Olivier Gossner et al., « Entropy bounds on Bayesian learning », HAL-SHS : économie et finance, ID : 10.1016/j.jmateco.2007.04.006
An observer of a process View the MathML source believes the process is governed by Q whereas the true law is P. We bound the expected average distance between P(xt|x1,...,xt−1) and Q(xt|x1,...,xt−1) for t=1,...,n by a function of the relative entropy between the marginals of P and Q on the n first realizations. We apply this bound to the cost of learning in sequential decision problems and to the merging of Q to P.