A prominent example of label-only privacy is in online advertising, where the goal is to predict conversionofanadimpression(thelabel)givenauser'sprofileandthespot'scontext(thefeatures).

General purpose models typically makefewassumptions about theunderlyingdata-structure and are known to perform well in the large-data regime. At the same time, there hasbeen growing interest inmodular neural architectures that represent thedata using sparsely interacting modules.

Colorsdesignatesupervision used: shadesofblue = highleveladvice; red = lowleveladvice; black = oracledemonstrations; gray = shaped rewards. Figure 6: "Bestadvice" is OffsetAdvice.

Akeyfeature ofCORN isthat it requires no ground truth 3D models or target view supervision.