# Jon Zero comments on Utility Maximization = Description Length Minimization

• If were so general that by judicious choice of you could impose an arbitrary distribution on then you’d pick the distribution that has , where . That is, a distribution where .

For me, that detracts a little from the entropy + KL divergence decomposition as applied to your utility maximisation problem. No balance point is reached; it’s all about the entropy term. Contrast with the bias/​variance trade-off (which has applicability to the reference class problem), where balance between the two parts of the decomposition is very important.

• It’s not quite all about the entropy term; it’s the KL-div term that determines which value is chosen. But you are correct insofar as this is not intended to be analogous to bias/​variance tradeoff, and it’s not really about “finding a balance point” between the two terms.