flâneur

Utility Maximization = Description Length Minimization — LessWrong

lesswrong.com · 10,365 words · saved by 1 readers

There’s a useful intuitive notion of “optimization” as pushing the world into a small set of states, starting from any of a large number of states. Visually: Yudkowsky and Flint both have notable formalizations of this “optimization as compression” idea. This post presents a formalization of optimization-as-compression grounded in information theory. Specifically: to “optimize” a system is to reduce the number of bits required to represent the system state using a particular encoding. In other words, “optimizing” a system means making it compressible (in the information-theoretic sense) by a particular model. This formalization turns out to be equivalent to expected utility maximization, and allows us to interpret any expected utility maximizer as “trying to make the world look like a particular model”. Before diving into the formalism, we’ll walk through a conceptual example, taken directly from Flint’s Ground of Optimization: building a house. Here’s Flint’s diagram: The key idea her

x Utility Maximization = Description Length Minimization — LessWrong Basic Foundations for Agent Models Information theory Optimization Utility Functions AI Rationality Curated 225 Utility Maximization = Description Length Minimization by johnswentworth 18th Feb 2021 AI Alignment Forum 7 min read 54 225 Ω 72 There’s a useful intuitive notion of “optimization” as pushing the world into a small set of states, starting from any of a large number of states. Visually: Yudkowsky and Flint both have notable formalizations of this “optimization as compression” idea. This post presents a formalization

related reading