Md. Asif Uddin

    Chapter 3 VI.3

    Interventions

    An intervention deletes the mechanism that generated a variable, and conditioning does not.

    An intervention deletes the mechanism that generated a variable.

    How this chapter is built

    M3Load-bearing

    The content is mathematics. Understanding is demonstrated by computation, not recall.

    basics1/11what the words mean
    concept2/2what to picture
    theory0/4why it works, and when it does not
    mathematics0/15derive it, then compute it
    practice0/9build it, break it, read the papers

    Five strands, not one. Mathematics is the spine; the other four are the body. A chapter cannot pay its way out of teaching with problems, nor out of problems with teaching.

    Before you start

    The problem

    Seeing and doing are different operations on the same graph. Making the difference formal — one deletes an edge, the other does not — is what turns a diagram into a calculus.

    Three pretext tasks built from one unlabelled imageAn unlabelled image feeds three tasks whose answers are known by construction: predict a hidden region, decide whether two crops came from the same photo, and recover an applied rotation. No annotator is involved.one unlabelled imageno labelhide a regionwhat was there?take two cropssame photo or not?rotate itby how much?The answer is known because you performed the corruption. What the model has to learn in order to undo it isthe representation you were after, and the choice of corruption decides which representation you get.
    Fig. 3 — Three tasks whose answers are known by construction, because you performed the corruption yourself.

    What this chapter covers

    • Do-operator
    • Intervention
    • Observational distribution
    • Interventional distribution

    Apparatus

    The mathematics this chapter leans on, held in Book 0 so it can be assumed here without being taught here. Not a gate — follow a link when a step stops making sense.

    Conditional independence 0.PR.05 · Bayes' rule 0.PR.04

    Notation

    • do(·)The intervention operator
    • X (random)A random variable
    • ⫫Statistical independence

    Propositions

    Not yet written. The topics above are the plan for this chapter; each will become a proposition with its own figure.

    Worked problems

    0/5 problems0/4 variants0/10 exercisesowes 15 more

    Not yet written. At M3 this chapter owes 5 worked problems across 4 distinct variants, and 10 exercises, every one with a published solution. The build enforces that from the day the chapter is marked published.