This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for instance, with standard boosting algorithms. Concretely, we first show that any...

Empirical evidence shows that entrepreneurs hold a large fraction of wealth, have higher saving rates than workers, and face substantial uninsurable entrepreneurial and investment risks. This paper constructs a heterogeneous-agent general equilibrium model with uninsurable entrepreneurial risk and capital-market imperfections to explore the implications of uninsurable entrepreneurial risk for w...

Let (X ,μ) be a probability space, set X to be distributed according to μ and put Y to be an unknown target random variable. In the usual setup in learning theory, one observes N independent couples (Xi, Yi)Ni=1 in X × R, distributed according to the joint distribution of X and Y . The goal is to construct a real-valued function f which is a good guess/prediction of Y . A standard way of measur...

Data warehouses (DWs) can become inconsistent when some dimensional constraints are not satisfied by the dimension instances. In this paper, we present preliminary results about the effects of the violation of partitioning constraints in homogeneous dimension instances over aggregation queries, and in particular over the summarizability property (SUMM) of the DWs. We are interested in finding w...

The purpose of this paper is to discuss empirical risk minimization when the losses are not necessarily bounded and may have a distribution with heavy tails. In such situations usual empirical averages may fail to provide reliable estimates and empirical risk minimization may provide large excess risk. However, some robust mean estimators proposed in the literature may be used to replace empiri...

In this note we study lower bounds on the empirical minimization algorithm. To explain the basic set up of this algorithm, let (Ω, μ) be a probability space and set X to be a random variable taking values in Ω, distributed according to μ. We are interested in the function learning (noiseless) problem, in which one observes n independent random variables X1, . . . , Xn distributed according to μ...

This paper deals with the representation of the family in Japanese TV commercials. Based on empirical research conducted in 2004 and 2005, it argues that Japanese commercials tend to depict the family and its members in highly stereotypical ways. Mothers are almost always shown doing some kind of housework, at times supported by their daughters, preparing for their future role as a mother and w...

Objectives Information technology involves a risk of privacy violation in providing easy access to confidential information,such as personal information and medical information through the Internet. In this study, we investigated medical information security to gain a better understanding of trends in research related to medical information security. Methods We researched papers published on ...