Talks
Fall 2015
The Sample Complexity of Revenue Maximization
Friday, October 16th, 2015, 11:15 am–11:45 am
Speaker:
Location:
Calvin Lab Auditorium
We explain how to use concepts from learning theory to make optimal auction theory more operational, replacing the “common prior” assumption with a data-driven approach. For example, we prove that in arbitrary single-parameter settings, one can learn an auction with expected revenue arbitrarily close to optimal from a polynomial number of samples from an unknown valuation distribution.