Coherent Belief Revision

Abstract:

Experts (human or computer) are often required to assess the probability of uncertain events. When a collection of experts independently assess events that are structurally interrelated, the resulting assessment may violate fundamental laws of probability. Such an assessment is termed incoherent. In this work we investigate how the problem of incoherence may be affected by allowing experts to specify likelihood models and then update their assessments based on the realization of a globally-observable random sequence.

Note: This material was originally presented in poster form at NIPS 2010.

Biography:

Peter Jones is a 4th year PhD student co-advised by Prof. Sanjoy Mitter and Prof. Venkatesh Saligrama (from BU). His research interests include the impact of indeterminancy and irrationality on complex systems and those systems' abilities to collectively assess risk and uncertainty.