The general problem of reconstructing an unknown function from a finite collection of samples is considered, in case the position of each input vector in the training set is not fixed beforehand, but is part of the learning process. In particular, the consistency of the Empirical Risk Minimization (ERM) principle is analyzed, when the points in the input space are generated by employing a purel...

Although there exist plentiful theories of empirical risk minimization (ERM) for supervised learning, current theoretical understandings of ERM for a related problem—stochastic convex optimization (SCO), are limited. In this work, we strengthen the realm of ERM for SCO by exploiting smoothness and strong convexity conditions to improve the risk bounds. First, we establish an Õ(d/n + √ F∗/n) ris...

Glossary AR(1): Autoregressive model of order one. The present state of a system can be described as a linear function of the state at the previous time, plus timeindependent noise. data assimilation: Method of optimally combining irregularly spaced observations with dynamical constraints to produce dynamically consistent fields on regular grids. CCA: Canonical Correlation Analysis EOF: Empiric...

This paper presents a model-based analysis of the introduction of green products, which are products with low environmental impacts. Both consumers and firms are simulated as populations of agents who differ in their behavioural characteristics. Model experiments illustrate the influence of behavioural characteristics on the success of switching to green consumption. The model reproduces empiri...

It is well-known that the skew-normal distribution can provide an alternative model to the normal distribution for analyzing asymmetric data. The aim of this paper is to propose two goodness-of-fit tests for assessing whether a sample comes from a multivariate skew-normal (MSN) distribution. We address the problem of multivariate skew-normality goodness-of-fit based on the empirical Laplace tra...

This paper provides the first systematic analysis of the choice of green office space by commercial tenants. We analyze the decisions of more than 11,000 tenants to choose office space in green buildings or in otherwise comparable non-green buildings located nearby. We formulate six propositions to explain why specific firms and industries may be more likely to lease green space. We test these ...

We present the Stochastic Green Function (SGF) algorithm designed for bosons on lattices. This new quantum Monte Carlo algorithm is independent of the dimension of the system, works in continuous imaginary time, and is exact (no error beyond statistical errors). Hamiltonians with several species of bosons (and one-dimensional Bose-Fermi Hamiltonians) can be easily simulated. Some important feat...

The present research studies and compares the effect of participating in team sports (soccer and volleyball) and individual sports (table tennis and badminton) on depression among high school students of Khoramdareh City in the period of 2006-2007. Research method is semi-empirical and the population of the research includes 1300 high school students of which 100 students with depression (rangi...

Multivariate vertical Empirical Orthogonal Functions (EOF) are calculated for the entire Mediterranean Sea both from observations and model simulations, in order to find the optimal number of vertical modes to represent the upper thermocline vertical structure. For the first time, we show that the large-scale Mediterranean thermohaline vertical structure can be represented by a limited number o...

Multivariate loss functions are used to assess performance in many modern prediction tasks, including information retrieval and ranking applications. Convex approximations are typically optimized in their place to avoid NP-hard empirical risk minimization problems. We propose to approximate the training data instead of the loss function by posing multivariate prediction as an adversarial game b...