PREFERRING SIMPLICITY

This paper examines circumstances under which a preference for simplicity enhances the eectiveness of inductive reasoning. We con- sider a game in which Fate chooses a data generating process and agents are characterized by inference rules that may or may not fa- vor simpler theories over more complex ones. The basic intuition is that agents who do not prefer simple theories to more complex ones are doomed to \overt" the data and therefore engage in ineective learning. The analysis places no computational or memory limitations on the agents|a preference for simplicity emerges in the presence of unlimited reasoning powers