On Wed, Apr 30, 2025 at 12:42 PM James Bowery <jabow...@gmail.com> wrote: > What I came up with was the widely cited "Causal inference using the > algorithmic Markov condition" by Janzing and Schölkopf. That paper argues > for a method, based on computable approximation of Kolmogorov Complexity, to > select from among different directed Acyclic graphs that model a standard > dataset. This is, of course, reminiscent of the, in my opinion, profoundly > misleading "MDL principle" as set forth by Rissanen in which the descriptive > codes were not Turing complete. at least their pedantry addresses some of Matt's and does so even without the requirement of directed Cyclic graphs to model datasets.
I think I understand. We say that X causes Y if we can describe Y as a function of X. If the simplest description of X and Y has the form Y = f(X), then we are using algorithmic information to find causality. For example, X Y - - 1 1 2 2 3 2 then I can write Y as a function of X, but not X as a function of Y. Thus, the DAG X -> Y is more plausible than Y -> X. To make this practical, the paper postulates a noise signal, as Y = f(X, N), where N can be 0 in the first case but not in the second. Thus, less algorithmic information is needed to encode the first case. -- -- Matt Mahoney, mattmahone...@gmail.com ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T0f47884dae19d52d-M1f5eca5720c58732f2ec5179 Delivery options: https://agi.topicbox.com/groups/agi/subscription
