lin-0052
3.1 From computational graphs to learning sketches
Let \(S\) be a directed graph of formal learning operations and let
be its free category. Objects of \(J\) can denote data, representations, predictions, policies, local sections, or world-model fragments. Its arrows are formal composites of encoders, transitions, interventions, restrictions, updates, and decision maps.
A bare graph says which composites can be formed. It does not say which composites ought to agree. A learning sketch adds that declaration.
A learning sketch is a quadruple
where:
\(S\) is a graph of formal learning operations;
\(\mathcal D\) is a family of equations between parallel paths;
\(\mathcal L\) is a family of designated cones; and
\(\mathcal K\) is a family of designated cocones.
The equations in \(\mathcal D\) generate a congruence \(\sim _{\mathcal D}\) on \(J=\operatorname {Path}(S)\) and hence a quotient
The three kinds of declaration play different roles. Path equations express route agreement. Designated cones express reconstruction, synchronization, or shared-state conditions. Designated cocones express aggregation, identification, or gluing. Treating all three as a single scalar penalty would erase this distinction.
Declare route equalities and universal properties separately. They can fail for different reasons, localize to different components, and require different repair languages.