Algorithmic Learning in a Random World¶
Vovk, V., Gammerman, A., & Shafer, G. 1. (2005). Algorithmic Learning in a Random World. Springer.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Out Of Distribution Detection
- Conformal prediction formalizes the same coupling differently, emitting a prediction set whose size grows as the input drifts from the calibration data, so the system's own output width signals departure from competence.
This sourceFoundational text on conformal prediction, which emits set-valued (region) predictions with validity guarantees; prediction-set size grows for inputs that conform poorly to the calibration data, signaling drift from the training distribution.
Supported in partVerified against the publisher's abstract
The publisher abstract places the book in confidence- and credibility-bearing prediction under an i.i.d. randomness assumption, but it never states conformal prediction sets or that set size grows as inputs drift from calibration data.
“Based on these approximations, a new set of machine learning algorithms have been developed that can be used to make predictions and to estimate their confidence and credibility in high-dimensional spaces under the usual assumption that the data are independent and identically distributed (assumption of randomness).”
- Conformal prediction formalizes the same coupling differently, emitting a prediction set whose size grows as the input drifts from the calibration data, so the system's own output width signals departure from competence.
Domain-specific¶
- Label Ambiguity
- The interventionist moves all follow from the one agreement-rate parameter: report metrics stratified by agreement bin; train and evaluate against soft labels that encode the agreement distribution rather than a hard call; let the model abstain (conformal prediction) in the disagreement zone instead of guessing
This sourceThe monograph that introduced conformal prediction, a set-valued method whose predictors report their own confidence and credibility.
Supported in partVerified against the work's full text
“Conformal predictors are among the most accurate methods of machine learning, and unlike other state-of-the-art methods, they provide information about their own accuracy and reliability”
- The interventionist moves all follow from the one agreement-rate parameter: report metrics stratified by agreement bin; train and evaluate against soft labels that encode the agreement distribution rather than a hard call; let the model abstain (conformal prediction) in the disagreement zone instead of guessing
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 2 of 2 citations: 2 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:a2b11c2e4953 · see in the full table