We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We prove sharp bounds for an existing framework of Gibbs algorithms, and ...
Many algorithms for grammatical inference can be viewed as instances of a more general algorithm which maintains a set of primitive elements, which distributionally define sets of ...
: In many prediction problems, including those that arise in computer security and computational finance, the process generating the data is best modeled as an adversary with whom ...
We address the problem of constructing randomized online algorithms for the Metrical Task Systems (MTS) problem on a metric against an oblivious adversary. Restricting our attenti...
Jacob Abernethy, Peter L. Bartlett, Niv Buchbinder...
We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed t...