Field crosswalk — Quantilizers

Quantilizers bound optimizer risk by sampling from a high-performing quantile rather than maximizing directly. Local quantile safety and distribution soundness transfer under explicit assumptions — but local quantile-safe action choice does not imply trajectory-level correction integrity.

What decision changes?

Use quantile restrictions as a local risk control, not as evidence that correction capacity survives capability growth or successor change.

Quantilization is an early answer to Goodhart under optimization: instead of taking the argmax, sample from the top quantile of a base policy. Taylor’s bound limits optimizer-induced risk when eligibility is sound.

The book treats quantile safety as a local projection — useful when paired with trajectory-level correction certificates, insufficient alone. Lean proves soundness transfer lemmas and a finite separation showing quantile-safe local actions can coexist with failed trajectory CCI. Chapter 27 groups quantilization with other tempting weaker invariants that fail the correction-channel stress test.

What quantilization keeps that this crosswalk does not replace: a concrete, analyzable sampling mechanism with a quantifiable risk/performance tradeoff. The book offers no closed-form knob of comparable simplicity.

Formulas

QuantSound(θ,P)  QuantSafeLocal(θ,x)  P(pt(x))\mathrm{QuantSound}(\theta,\mathcal P)\ \wedge\ \mathrm{QuantSafeLocal}(\theta,x)\ \Rightarrow\ \mathcal P(\mathrm{pt}(x))
Forward projection: quantile eligibility soundness transfers to the sampled point under the quantilizer setup. (ch27)
QuantileSafeLocalAction  ¬TrajectoryCCIPreserved\mathrm{QuantileSafeLocalAction}\ \wedge\ \neg\mathrm{TrajectoryCCIPreserved}
Non-converse separation: local quantile-safe choices without trajectory CCI preservation. (ch27)