b19aa25ff58940d974234b48391b9549-Paper.pdf

Neural Information Processing Systems 

Wethenpropose newalgorithms that,givenonly an"approximate distribution" forthe bidder'svaluation, can learn amechanism whose revenue is nearly optimal simultaneously for all "true distributions" that are α-close to the original distribution in Kolmogorov-Smirnov distance.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found