BibTeX Export for Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions

Copy to Clipboard Download

@InProceedings{panageas_et_al:LIPIcs.ITCS.2017.2,
  author =	{Panageas, Ioannis and Piliouras, Georgios},
  title =	{{Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions}},
  booktitle =	{8th Innovations in Theoretical Computer Science Conference (ITCS 2017)},
  pages =	{2:1--2:12},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-029-3},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{67},
  editor =	{Papadimitriou, Christos H.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2017.2},
  URN =		{urn:nbn:de:0030-drops-81640},
  doi =		{10.4230/LIPIcs.ITCS.2017.2},
  annote =	{Keywords: Gradient Descent, Center-stable manifold, Saddle points, Hessian}
}

The metadata provided by Dagstuhl Publishing on its webpages, as well as their export formats (such as XML or BibTeX) available at our website, is released under the CC0 1.0 Public Domain Dedication license. That is, you are free to copy, distribute, use, modify, transform, build upon, and produce derived works from our data, even for commercial purposes, all without asking permission. Of course, we are always happy if you provide a link to us as the source of the data.

Read the full CC0 1.0 legal code for the exact terms that apply: https://creativecommons.org/publicdomain/zero/1.0/legalcode