flâneur

Research update: Towards a Law of Iterated Expectations for Heuristic Estimators — LessWrong

lesswrong.com · 223 words · saved by 1 readers

Last week, ARC released a paper called Towards a Law of Iterated Expectations for Heuristic Estimators, which follows up on previous work on formalizing the presumption of independence. Most of the work described here was done in 2023. A brief table of contents for this post: In "Formalizing the Presumption of Independence", we defined a heuristic estimator to be a hypothetical algorithm that estimates the values of mathematical expression based on arguments. That is, a heuristic estimator is an algorithm G that takes as input -- and outputs an estimate of the value of Y that incorporates the information provided by π 1 , … , π m . We denote this estimate by G ( Y ∣ π 1 , … , π m ) .[1] In that paper, we introduced the following question: is there a computationally efficient heuristic estimator that formalizes intuitively valid reasoning about the values of mathematical quantities based on arguments? We studied the question by introducing intuitively desirable coherence propertie

x Research update: Towards a Law of Iterated Expectations for Heuristic Estimators — LessWrong World Modeling AI Frontpage 87 Research update: Towards a Law of Iterated Expectations for Heuristic Estimators by Eric Neyman 7th Oct 2024 AI Alignment Forum 27 min read 2 87 Ω 38 Last week, ARC released a paper called Towards a Law of Iterated Expectations for Heuristic Estimators , which follows up on previous work on formalizing the presumption of independence . Most of the work described here was done in 2023. A brief table of contents for this post: What is a heuristic estimator? (One example a

related reading