claim

active

claim:if-one-were-to-use-the-bethe-approximation-the-corresponding-dynamics-coincide-with-belief-propagation

If one were to use the Bethe approximation, the corresponding dynamics coincide with belief propagation.

Alternative free energy approximation yields belief propagation.

Source paper

extracted_from

Active inference on discrete state-spaces: a synthesis

(2020) · Lancelot Da Costa · Thomas Parr · Noor Sajid · Sebastijan Veselic +2

Neighborhood — ranked by edge-count

Methods (1)

method

Belief Propagation
supports
Inference mechanism underlying active inference; updates posterior beliefs via gradient descent on free energy.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Bethe Approximationframework0.808
Free energy approximation using two-node marginals.
These dynamics are consistent with predictive processing since active inference prescribes dynamics that minimise prediction error.concept0.782
Connection between active inference neuronal dynamics and predictive processing theory.
probably helps not only with faithful reconstruction but also creates interference patterns that encode nuanced information about the deltas and convergences between states.quote0.765
Key quote connecting path redundancy to interferometric information encoding.
Under the Markov blanket assumption together with NESS, a generalised synchrony appears, such that the dynamics of internal states can be cast as performing inference over external states via minimisation of variational free energy.claim0.760
Key theoretical claim linking active inference to physics in Section 2.
If a system attains a general steady-state, it will appear to behave in a Bayes optimal fashion, both in terms of optimal Bayesian design (exploration) and Bayesian decision theory (exploitation).hypothesis0.756
Corollary 3 in Appendix B derived from steady-state assumptions.
Echoes of similar proportions and angles appear throughout any natural system due to uniform underlying processes, giving a consistent character to different parts.claim0.753
Does the multi-directional nature of truth imply an underlying nonlinear representation, or is it compatible with linear separability?question0.753
Theoretical open question about the geometry of truth in LLMs raised in Discussion
The model converges to a more stable truth direction in middle-to-late layers, as evidenced by increasing cosine similarity between layer-wise probes.claim0.753
Supported by the geometric transition visible in cosine similarity heatmaps for F0-F3.