Bounds on the minimax rate for estimating a prior over a VC class from independent learning tasks
نویسندگان
چکیده
Abstract. We study the optimal rates of convergence for estimating a prior distribution over a VC class from a sequence of independent data sets respectively labeled by independent target functions sampled from the prior. We specifically derive upper and lower bounds on the optimal rates under a smoothness condition on the correct prior, with the number of samples per data set equal the VC dimension. These results have implications for the improvements achievable via transfer learning. We additionally extend this setting to real-valued function, where we establish consistency of an estimator for the prior, and discuss an additional application to a preference elicitation problem in algorithmic economics.
منابع مشابه
Strong Minimax Lower Bounds for Learning
Known minimax lower bounds for learning state that for each sample size n, and learning rule g n , there exists a distribution of the observation X and a concept C to be learnt such that the expected error of g n is at least a constant times V =n, where V is the VC dimension of the concept class. However, these bounds do no tell anything about the rate of decrease of the error for a xed distrib...
متن کاملStrong minimax lower bounds for learning
Minimax lower bounds for concept learning state, for example, that for each sample size n and learning rule gn, there exists a distribution of the observation X and a concept C to be learnt such that the expected error of gn is at least a constant times V=n, where V is the vc dimension of the concept class. However, these bounds do not tell anything about the rate of decrease of the error for a...
متن کاملMinimax Estimator of a Lower Bounded Parameter of a Discrete Distribution under a Squared Log Error Loss Function
The problem of estimating the parameter ?, when it is restricted to an interval of the form , in a class of discrete distributions, including Binomial Negative Binomial discrete Weibull and etc., is considered. We give necessary and sufficient conditions for which the Bayes estimator of with respect to a two points boundary supported prior is minimax under squared log error loss function....
متن کاملEfficient Policy Learning
We consider the problem of using observational data to learn treatment assignment policies that satisfy certain constraints specified by a practitioner, such as budget, fairness, or functional form constraints. This problem has previously been studied in economics, statistics, and computer science, and several regret-consistent methods have been proposed. However, several key analytical compone...
متن کاملEstimating a Bounded Normal Mean Relative to Squared Error Loss Function
Let be a random sample from a normal distribution with unknown mean and known variance The usual estimator of the mean, i.e., sample mean is the maximum likelihood estimator which under squared error loss function is minimax and admissible estimator. In many practical situations, is known in advance to lie in an interval, say for some In this case, the maximum likelihood estimator...
متن کامل