Surface Smoothness and Statistical Method (Ist Report)

Exploiting Smoothness in Statistical Learning, Sequential Prediction, and Stochastic Optimization

Exploiting Smoothness in Statistical Learning, Sequential Prediction, and Stochastic Optimization

IST programme ( 5 th FP ) ESCORT IST 1999 - 20006 D 2011 report STATE OF THE ART

Information Society Technologies (ist) Programme Project Ist-2001-33562 Mowgli Report N. D5.a Distributed Knowledge Management and Version Control

We propose an infrastructure for collaborative content management and version control for structured mathematical knowledge. This will enable multiple users to work jointly on mathematical theories with minimal interference. We describe the API and the functionality needed to realize a CVS-like version control and distribution model. This architecture extends the CVS architecture in two ways, m...

RSG: Beating Subgradient Method without Smoothness and Strong Convexity

In this paper, we study the efficiency of a Restarted SubGradient (RSG) method that periodically restarts the standard subgradient method (SG). We show that, when applied to a broad class of convex optimization problems, RSG method can find an ǫ-optimal solution with a low complexity than SG method. In particular, we first show that RSG can reduce the dependence of SG’s iteration complexity on ...

A Comparison of Different Methods of Paper Surface Smoothness Evaluation

Smoothness of paper surface is an important property from its printability. A number of techniques are available for characterizing the topographical features of the paper surface. These techniques have led to the development of smoothness testers of various types such as airleak testers, optical contact testers, surface profilers, and a number of ink and liquid application apparatus to assess ...