Estimation in tournaments under strong stochastic transitivity
Statement
For a tournament of teams, observe jointly independent for , with for , for , and . Assume there is an unknown ordering of the teams satisfying strong stochastic transitivity: if team ranks higher than team , then for every team . Estimate the probability matrix under mean squared error loss. The report claims that the overall least-squares estimator attains the minimax rate up to logarithmic factors, whereas its computationally tractable two-stage estimator has maximum squared-error risk up to logarithmic factors, with up to logarithmic factors on several specified subclasses.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.