Header logo is

4 results (View BibTeX file of all listed publications)

2012

no image
The principles of XMCD and its application to L-edges in transition metals

Schütz, G.

In Linear and Chiral Dichroism in the Electron Miroscope, pages: 23-42, Pan Stanford Publishing Pte.Ltd., Singapore, 2012 (incollection)

mms

[BibTex]

2012

mms Schütz, G. The principles of XMCD and its application to L-edges in transition metals In Linear and Chiral Dichroism in the Electron Miroscope, pages: 23-42, Pan Stanford Publishing Pte.Ltd., Singapore, 2012 (incollection)

[BibTex]

no image
Structural and chemical characterization on the nanoscale

Stierle, A., Carstanjen, H.-D., Hofmann, S.

In Nanoelectronics and Information Technology. Advanced Electronic Materials and Novel Devices, pages: 233-254, Wiley-VCH, Weinheim, 2012 (incollection)

mms

[BibTex]

mms Stierle, A., Carstanjen, H.-D., Hofmann, S. Structural and chemical characterization on the nanoscale In Nanoelectronics and Information Technology. Advanced Electronic Materials and Novel Devices, pages: 233-254, Wiley-VCH, Weinheim, 2012 (incollection)

[BibTex]

no image
Rutherford Backscattering

Carstanjen, H. D.

In Nanoelectronics and Information Technology. Advanced Electronic Materials and Novel Devices, pages: 250-252, WILEY-VCH Verlag, Weinheim, Germany, 2012 (incollection)

mms

[BibTex]

mms Carstanjen, H. D. Rutherford Backscattering In Nanoelectronics and Information Technology. Advanced Electronic Materials and Novel Devices, pages: 250-252, WILEY-VCH Verlag, Weinheim, Germany, 2012 (incollection)

[BibTex]

2011

no image
Projected Newton-type methods in machine learning

Schmidt, M., Kim, D., Sra, S.

In Optimization for Machine Learning, pages: 305-330, MIT Press, Cambridge, MA, USA, 2011 (incollection)

Abstract
{We consider projected Newton-type methods for solving large-scale optimization problems arising in machine learning and related fields. We first introduce an algorithmic framework for projected Newton-type methods by reviewing a canonical projected (quasi-)Newton method. This method, while conceptually pleasing, has a high computation cost per iteration. Thus, we discuss two variants that are more scalable, namely, two-metric projection and inexact projection methods. Finally, we show how to apply the Newton-type framework to handle non-smooth objectives. Examples are provided throughout the chapter to illustrate machine learning applications of our framework.}

mms

link (url) [BibTex]

2011

mms Schmidt, M., Kim, D., Sra, S. Projected Newton-type methods in machine learning In Optimization for Machine Learning, pages: 305-330, MIT Press, Cambridge, MA, USA, 2011 (incollection)

link (url) [BibTex]