We consider the problem of decision-making with side information and unbounded loss functions. Inspired by probably approximately correct learning model, we use a slightly differe...
We de ne the sharply bounded hierarchy, SBH(QL), a hierarchy of classes within P, using quasilinear-time computation and quanti cation over strings of length logn. It generalizes ...
Stephen A. Bloch, Jonathan F. Buss, Judy Goldsmith
We present a higher-order functional notation for polynomial-time computation with arbitrary 0; 1-valued oracle. This provides a linguistic characterization for classes such as np...
We review and slightly strengthen known results on the Kolmogorov complexity of prefixes of effectively random sequences. First, there are recursively random random sequences su...
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...