PUMA publications for /user/mathematik/svmshttps://puma.ub.uni-stuttgart.de/user/mathematik/svmsPUMA RSS feed for /user/mathematik/svms2024-03-29T10:32:09+01:00- Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimensionhttps://puma.ub.uni-stuttgart.de/bibtex/21c9c2f95740fa5fedbf857e29aecc964/mathematikmathematik2021-12-15T15:34:24+01:00myown from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="T. Hamm" itemprop="url" href="/person/1775016bfeed92d8ee62143eb93798ff1/author/0"><span itemprop="name">T. Hamm</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1775016bfeed92d8ee62143eb93798ff1/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Ann. Statist.</span>, </em> </span>(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)<em>https://arxiv.org/abs/2003.06202.</em></span>Wed Dec 15 15:34:24 CET 2021Ann. Statist.\url{https://arxiv.org/abs/2003.06202}3153--3180Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension492021myown from:ingosteinwart svms
- liquidSVM: A Fast and Versatile SVM Packagehttps://puma.ub.uni-stuttgart.de/bibtex/21fcad3c2f4bc1a3373f58f912a6f8e7b/mathematikmathematik2021-10-06T13:25:03+02:00myown svm_opt from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/113f79e7ebac84dc1fbe577e28dbeb1bc/author/0"><span itemprop="name">I. Steinwart</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="P. Thomann" itemprop="url" href="/person/113f79e7ebac84dc1fbe577e28dbeb1bc/author/1"><span itemprop="name">P. Thomann</span></a></span></span>. </span><span class="additional-entrytype-information"><em><span itemprop="producer">Fakultät für Mathematik und Physik, Universität Stuttgart</span>, </em>(<em><span>2017<meta content="2017" itemprop="datePublished"/></span></em>)</span>Wed Oct 06 13:25:03 CEST 2021\url{https://arxiv.org/abs/1702.06899}{liquidSVM}: A Fast and Versatile {SVM} Package2017myown svm_opt from:ingosteinwart svms
- Learning with Hierarchical Gaussian Kernelshttps://puma.ub.uni-stuttgart.de/bibtex/2a6ff01a31ca06a259e853196bad49db6/mathematikmathematik2021-10-06T13:25:03+02:00myown svm_opt from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1ff3ebe455d4be80e55f263c9a291dae8/author/0"><span itemprop="name">I. Steinwart</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="P. Thomann" itemprop="url" href="/person/1ff3ebe455d4be80e55f263c9a291dae8/author/1"><span itemprop="name">P. Thomann</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="N. Schmid" itemprop="url" href="/person/1ff3ebe455d4be80e55f263c9a291dae8/author/2"><span itemprop="name">N. Schmid</span></a></span></span>. </span><span class="additional-entrytype-information"><em><span itemprop="producer">Fakultät für Mathematik und Physik, Universität Stuttgart</span>, </em>(<em><span>2016<meta content="2016" itemprop="datePublished"/></span></em>)</span>Wed Oct 06 13:25:03 CEST 2021\url{http://arxiv.org/abs/1612.00824}Learning with Hierarchical {G}aussian Kernels2016myown svm_opt from:ingosteinwart svms
- Intrinsic Dimension Adaptive Partitioning for Kernel Methodshttps://puma.ub.uni-stuttgart.de/bibtex/212d891497f4d4cb30bbe0768fa22ce99/mathematikmathematik2021-10-06T13:22:57+02:00myown from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="T. Hamm" itemprop="url" href="/person/1e441e671e01121056000bdc80339f421/author/0"><span itemprop="name">T. Hamm</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1e441e671e01121056000bdc80339f421/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><em><span itemprop="producer">Fakultät für Mathematik und Physik, Universität Stuttgart</span>, </em>(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)</span>Wed Oct 06 13:22:57 CEST 2021\url{https://arxiv.org/abs/2107.07750}Intrinsic Dimension Adaptive Partitioning for Kernel Methods2021myown from:ingosteinwart svms
- Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimensionhttps://puma.ub.uni-stuttgart.de/bibtex/256e55781630355c8a835ebc8b2d375be/mathematikmathematik2021-10-06T13:22:57+02:00myown from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="T. Hamm" itemprop="url" href="/person/1775016bfeed92d8ee62143eb93798ff1/author/0"><span itemprop="name">T. Hamm</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1775016bfeed92d8ee62143eb93798ff1/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Ann. Statist.</span>, </em> </span>(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)<em>https://arxiv.org/abs/2003.06202.</em></span>Wed Oct 06 13:22:57 CEST 2021Ann. Statist.\url{https://arxiv.org/abs/2003.06202}Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension2021myown from:ingosteinwart svms
- Optimal Learning with Anisotropic Gaussian SVMshttps://puma.ub.uni-stuttgart.de/bibtex/2617a4525f4ba01fa1f940f71c7621ad9/mathematikmathematik2021-10-06T13:22:56+02:00myown from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="H. Hang" itemprop="url" href="/person/1cfe68897756d95b2f04832076465e27a/author/0"><span itemprop="name">H. Hang</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1cfe68897756d95b2f04832076465e27a/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Appl. Comput. Harmon. Anal.</span>, </em> </span>(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)<em>https://arxiv.org/abs/1810.02321.</em></span>Wed Oct 06 13:22:56 CEST 2021Appl. Comput. Harmon. Anal.\url{https://arxiv.org/abs/1810.02321}55337-367Optimal Learning with Anisotropic {G}aussian {SVM}s2021myown from:ingosteinwart svms
- Optimal Rates for Regularized Least Squares Regressionhttps://puma.ub.uni-stuttgart.de/bibtex/2e44eaaf2c5164b42dd38552e2b4194d9/mathematikmathematik2021-07-05T20:23:57+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1f8d8d0842e5cab02bcd7a989efed9fb2/author/0"><span itemprop="name">I. Steinwart</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="D. Hush" itemprop="url" href="/person/1f8d8d0842e5cab02bcd7a989efed9fb2/author/1"><span itemprop="name">D. Hush</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="C. Scovel" itemprop="url" href="/person/1f8d8d0842e5cab02bcd7a989efed9fb2/author/2"><span itemprop="name">C. Scovel</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Proceedings of the 22nd Annual Conference on Learning Theory</span>, </em></span><em>page <span itemprop="pagination">79--93</span>. </em>(<em><span>2009<meta content="2009" itemprop="datePublished"/></span></em>)<em>http://www.cs.mcgill.ca/~colt2009/papers/038.pdf.</em></span>Mon Jul 05 20:23:57 CEST 2021Proceedings of the 22nd {A}nnual {C}onference on {L}earning {T}heory\url{http://www.cs.mcgill.ca/~colt2009/papers/038.pdf}79--93Optimal Rates for Regularized Least Squares Regression2009from:ingosteinwart svms
- Robust learning from bites for data mininghttps://puma.ub.uni-stuttgart.de/bibtex/2186dd1b6fe372d0832d60cf876a33d75/mathematikmathematik2021-07-05T20:23:57+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="A. Christmann" itemprop="url" href="/person/13d47215250cc046d6cd8c8642713fc9b/author/0"><span itemprop="name">A. Christmann</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/13d47215250cc046d6cd8c8642713fc9b/author/1"><span itemprop="name">I. Steinwart</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="M. Hubert" itemprop="url" href="/person/13d47215250cc046d6cd8c8642713fc9b/author/2"><span itemprop="name">M. Hubert</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Comput. Statist. Data Anal.</span>, </em> </span>(<em><span>2007<meta content="2007" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:23:57 CEST 2021Comput. Statist. Data Anal.347--361Robust learning from bites for data mining522007from:ingosteinwart svms
- Fast rates for support vector machines using Gaussian kernelshttps://puma.ub.uni-stuttgart.de/bibtex/2c59943da7855d838b764d478c5c05543/mathematikmathematik2021-07-05T20:23:36+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/17d1fdca7cb2e03102ad4b3e006158cc6/author/0"><span itemprop="name">I. Steinwart</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="C. Scovel" itemprop="url" href="/person/17d1fdca7cb2e03102ad4b3e006158cc6/author/1"><span itemprop="name">C. Scovel</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Ann. Statist.</span>, </em> </span>(<em><span>2007<meta content="2007" itemprop="datePublished"/></span></em>)<em>http://arxiv.org/pdf/0708.1838.</em></span>Mon Jul 05 20:23:36 CEST 2021Ann. Statist.\url{http://arxiv.org/pdf/0708.1838}575--607Fast rates for support vector machines using {G}aussian kernels352007from:ingosteinwart svms
- Some Remarks on the Statistical Analysis of SVMs and Related Methodshttps://puma.ub.uni-stuttgart.de/bibtex/22a3ccc6ca7479aa8d349a61828cee560/mathematikmathematik2021-07-05T20:23:35+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1f1ca0f22347897a5e501947e27005087/author/0"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Empirical Inference -- Festschrift in Honor of Vladimir N. Vapnik</span>, </em><em>chapter 4, </em><em><span itemprop="publisher">Springer</span>, </em><em>Berlin, </em></span>(<em><span>2013<meta content="2013" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:23:35 CEST 2021BerlinEmpirical Inference -- Festschrift in Honor of Vladimir N. Vapnik425-36Some Remarks on the Statistical Analysis of {SVM}s and Related Methods2013from:ingosteinwart svms
- Stability of unstable learning algorithmshttps://puma.ub.uni-stuttgart.de/bibtex/2282b96e791d5d701dca689593817a59b/mathematikmathematik2021-07-05T20:23:35+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="D. Hush" itemprop="url" href="/person/1b930699b1fb5dc1289de0a577f575efc/author/0"><span itemprop="name">D. Hush</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="C. Scovel" itemprop="url" href="/person/1b930699b1fb5dc1289de0a577f575efc/author/1"><span itemprop="name">C. Scovel</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1b930699b1fb5dc1289de0a577f575efc/author/2"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Mach. Learn.</span>, </em> </span>(<em><span>2007<meta content="2007" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:23:35 CEST 2021Mach. Learn.197--206Stability of unstable learning algorithms672007from:ingosteinwart svms
- Sparseness of support vector machines---some asymptotically sharp boundshttps://puma.ub.uni-stuttgart.de/bibtex/26cc1c0ae892dbf61ff14058d1c3cb9fe/mathematikmathematik2021-07-05T20:23:35+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/18b034823dd6f7f6b30a77255773a46c2/author/0"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Advances in Neural Information Processing Systems 16</span>, </em></span><em>page <span itemprop="pagination">1069--1076</span>. </em><em>Cambridge, MA, </em><em><span itemprop="publisher">MIT Press</span>, </em>(<em><span>2004<meta content="2004" itemprop="datePublished"/></span></em>)<em>http://books.nips.cc/papers/files/nips16/NIPS2003_LT01.pdf.</em></span>Mon Jul 05 20:23:35 CEST 2021Cambridge, MAAdvances in Neural Information Processing Systems 16\url{http://books.nips.cc/papers/files/nips16/NIPS2003_LT01.pdf}1069--1076Sparseness of support vector machines---some asymptotically sharp bounds2004from:ingosteinwart svms
- On the optimal parameter choice for $\nu$-support vector machineshttps://puma.ub.uni-stuttgart.de/bibtex/26b78efdcc4b4c720d2c9bdffa26fa9a5/mathematikmathematik2021-07-05T20:23:35+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1554322ecec43c9e020476692dada1282/author/0"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">IEEE Transactions on Pattern Analysis and Machine Intelligence</span>, </em> </span>(<em><span>2003<meta content="2003" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:23:35 CEST 2021IEEE Transactions on Pattern Analysis and Machine Intelligence1274--1284On the optimal parameter choice for $\nu$-support vector machines252003from:ingosteinwart svms
- Sparsity of SVMs that use the $\epsilon$-insensitive losshttps://puma.ub.uni-stuttgart.de/bibtex/270f813cf46bce61179df6111462a52b1/mathematikmathematik2021-07-05T20:23:35+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1982a8c4b98cdb69e46f16c9b0b189aaf/author/0"><span itemprop="name">I. Steinwart</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="A. Christmann" itemprop="url" href="/person/1982a8c4b98cdb69e46f16c9b0b189aaf/author/1"><span itemprop="name">A. Christmann</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Advances in Neural Information Processing Systems 21</span>, </em></span><em>page <span itemprop="pagination">1569--1576</span>. </em>(<em><span>2009<meta content="2009" itemprop="datePublished"/></span></em>)<em>http://books.nips.cc/papers/files/nips21/NIPS2008_0274.pdf.</em></span>Mon Jul 05 20:23:35 CEST 2021Advances in Neural Information Processing Systems 21\url{http://books.nips.cc/papers/files/nips21/NIPS2008_0274.pdf}1569--1576Sparsity of {SVM}s that use the $\epsilon$-insensitive loss2009from:ingosteinwart svms
- Support vector machines are universally consistenthttps://puma.ub.uni-stuttgart.de/bibtex/27f7f42364fba1a42358e74eff8a390bb/mathematikmathematik2021-07-05T20:23:35+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/148c3d4e60eb5e6cb735b7d4de449ad2b/author/0"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">J. Complexity</span>, </em> </span>(<em><span>2002<meta content="2002" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:23:35 CEST 2021J. Complexity768--791Support vector machines are universally consistent182002from:ingosteinwart svms
- Optimal regression rates for SVMs using Gaussian kernelshttps://puma.ub.uni-stuttgart.de/bibtex/237f3c67f71c1b2f735efdc48571a62bb/mathematikmathematik2021-07-05T20:20:45+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="M. Eberts" itemprop="url" href="/person/1a94061153c06a286ed022bb93a6e7eb2/author/0"><span itemprop="name">M. Eberts</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1a94061153c06a286ed022bb93a6e7eb2/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Electron. J. Stat.</span>, </em> </span>(<em><span>2013<meta content="2013" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:20:45 CEST 2021Electron. J. Stat.1--42Optimal regression rates for {SVM}s using {G}aussian kernels72013from:ingosteinwart svms
- Optimal Learning Rates for Localized SVMshttps://puma.ub.uni-stuttgart.de/bibtex/253ec3f8b02b72a44ba6bd902fad667ee/mathematikmathematik2021-07-05T20:20:45+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="M. Meister" itemprop="url" href="/person/15dcd58c2d7c574ba40bc25c707f232cc/author/0"><span itemprop="name">M. Meister</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/15dcd58c2d7c574ba40bc25c707f232cc/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">J. Mach. Learn. Res.</span>, </em> </span>(<em><span>2016<meta content="2016" itemprop="datePublished"/></span></em>)<em>http://www.jmlr.org/papers/volume17/14-023/14-023.pdf.</em></span>Mon Jul 05 20:20:45 CEST 2021J. Mach. Learn. Res.\url{http://www.jmlr.org/papers/volume17/14-023/14-023.pdf}1-44Optimal Learning Rates for Localized {SVM}s172016from:ingosteinwart svms
- Consistency of support vector machines and other regularized kernel machineshttps://puma.ub.uni-stuttgart.de/bibtex/2abfd05598d4af1d2629a086b79d5e10b/mathematikmathematik2021-07-05T20:20:44+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1b2bf352260ff45e8461398dc92a306f5/author/0"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">IEEE Trans. Inform. Theory</span>, </em> </span>(<em><span>2005<meta content="2005" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:20:44 CEST 2021IEEE Trans. Inform. Theory128--142Consistency of support vector machines and other regularized kernel machines512005from:ingosteinwart svms
- Support Vector Machineshttps://puma.ub.uni-stuttgart.de/bibtex/24b7c2628eabe332e9f0ce34cf0cb6299/mathematikmathematik2021-07-05T20:20:44+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1a6ce469e51e80419b840b7be375577d2/author/0"><span itemprop="name">I. Steinwart</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="A. Christmann" itemprop="url" href="/person/1a6ce469e51e80419b840b7be375577d2/author/1"><span itemprop="name">A. Christmann</span></a></span></span>. </span><span class="additional-entrytype-information"><em><span itemprop="publisher">Springer</span>, </em><em>New York, </em>(<em><span>2008<meta content="2008" itemprop="datePublished"/></span></em>)</span>Mon Jul 05 20:20:44 CEST 2021New YorkSupport Vector Machines2008from:ingosteinwart svms
- Consistency and robustness of kernel-based regression in convex risk minimizationhttps://puma.ub.uni-stuttgart.de/bibtex/29d5ab335b6bc08ec702bd09a5ba087a8/mathematikmathematik2021-07-05T20:20:44+02:00from:ingosteinwart svms <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="A. Christmann" itemprop="url" href="/person/1850239ca0965e654006165feb4983abb/author/0"><span itemprop="name">A. Christmann</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="I. Steinwart" itemprop="url" href="/person/1850239ca0965e654006165feb4983abb/author/1"><span itemprop="name">I. Steinwart</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Bernoulli</span>, </em> </span>(<em><span>2007<meta content="2007" itemprop="datePublished"/></span></em>)<em>http://arxiv.org/pdf/0709.0626.</em></span>Mon Jul 05 20:20:44 CEST 2021Bernoulli\url{http://arxiv.org/pdf/0709.0626}799--819Consistency and robustness of kernel-based regression in convex risk minimization132007from:ingosteinwart svms