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...
We present an analysis of concentration-of-expectation phenomena in layered Bayesian networks that use generalized linear models as the local conditional probabilities. This frame...
We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a cla...
We use a Bayesian approach to optimally solve problems in noisy binary search. We deal with two variants: • Each comparison is erroneous with independent probability 1 − p. ...
The problem of on-line bin packing restricted to instances with only two item sizes (known in advance) has a well-known lower bound of 4/3 for its asymptotic competitive ratio. We...