A self-improvement procedure has an unusual incentive to find weaknesses in its own measurements. It searches repeatedly, retains favorable results, and changes the way later candidates are generated. A validation number can therefore become part of the training information even when it is never called a training label. This is a central issue in adaptive data analysis [13].
Machine-Native ReasoningReading edition
65. Evidence and recursive continuation
Reading tools
Reading library
Text settings
Saved in this browser for reading chapters. Browser zoom also works.
Loading chapter…