Simultaneous learning and prediction
Loizos Michael · 2014
Agents in real-world environments may have only par-tial access to available information, often in an arbitrary, or hard to model, manner. By reasoning with knowledge at their disposal, agents may hope to recover some miss-ing information. By acquiring the knowledge through a process of learning, the agents may further hope to guar-antee that the recovered information is indeed correct. Assuming only a black-box access to a learning process and a prediction process that are able to cope with miss-ing information in some principled manner, we examine how the two processes should interact so that they im-prove their overall joint performance. We identify nat-ural scenarios under which the interleaving of the pro-cesses is provably beneficial over their independent use.