We prove a theorem about the relative entropy of quantum states, which roughly states that if the relative entropy, S(ρ‖σ) ∆ = Tr ρ(log ρ− log σ), of two quantum states ρ and σ is at most c, then ρ/2 ‘sits inside’ σ. Using this ‘substate’ theorem, we give tight lower bounds for the privacy loss of bounded error quantum communication protocols for the index function problem. We also give tight l...

achieving optimal production cycle time for improving manufacturing processes is one of the common problems in production planning. during recent years, different approaches have been developed for solving this problem, but most of them assume that mean quality characteristic is constant over production run length and sets it on customer’s target value. however, the process mean may drift from ...

the problems of sequential change-point have several important applications in quality control, signal processing, and failure detection in industry and finance. we discuss a bayesian approach in the context of statistical process control: at an unknown time $tau$, the process behavior changes and the distribution of the data changes from p0 to p1. two cases are considered: (i) p0 and p1 are fu...

Some examples of absurd uniformly minimum variance unbiased estimators are discussed. Two reasons, argued in the literature, for having such estimators are lack of enough information in the available data and property of unbiasedness. In this paper, accepting both of these views, we show that an appropriate choice of loss function using a general concept of unbiasedness leads to risk unb...

This paper presents a computation of the Vγ dimension for regression in bounded subspaces of Reproducing Kernel Hilbert Spaces (RKHS) for the Support Vector Machine (SVM) regression ǫ-insensitive loss function Lǫ, and general Lp loss functions. Finiteness of the Vγ dimension is shown, which also proves uniform convergence in probability for regression machines in RKHS subspaces that use the Lǫ ...

Let {Xn, n >= 1} be a strictly stationary sequence of negatively associated random variables, with common continuous and bounded distribution function F. In this paper, we consider the estimation of the two-dimensional distribution function of (X1,Xk+1) based on histogram type estimators as well as the estimation of the covariance function of the limit empirical process induced by the se...

The quality loss function developed by Genichi Taguchi considers three cases, nominal-thebest, smaller-the-better, and larger-the-better. The methodology used to deal with the larger-thebetter case is slightly different than the other two cases. This research employs a term called target-mean ratio to propose a common formula for all three cases to bring about similarity among them. The target-...

In a market with partial information we consider the optimal selection of portfolios for utility maximizing investors under joint budget and shortfall risk constraints. The shortfall risk is measured in terms of expected loss. Stock returns satisfy a stochastic differential equation. Under general conditions on the corresponding drift process we provide the optimal trading strategy using Mallia...

In this paper, we study the generalization properties of online learning based stochastic methods for supervised learning problems where the loss function is dependent on more than one training sample (e.g., metric learning, ranking). We present a generic decoupling technique that enables us to provide Rademacher complexity-based generalization error bounds. Our bounds are in general tighter th...