<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>regularization | Michael Aerni</title><link>https://www.michaelaerni.com/tag/regularization/</link><atom:link href="https://www.michaelaerni.com/tag/regularization/index.xml" rel="self" type="application/rss+xml"/><description>regularization</description><generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><lastBuildDate>Mon, 09 Aug 2021 00:00:00 +0000</lastBuildDate><image><url>https://www.michaelaerni.com/media/icon_hua9c6b47fafe860101b75091fc8397190_346273_512x512_fill_lanczos_center_3.png</url><title>regularization</title><link>https://www.michaelaerni.com/tag/regularization/</link></image><item><title>Interpolation can hurt robust generalization even when there is no noise</title><link>https://www.michaelaerni.com/publication/interpolation-can-hurt-robust-generalization-even-when-there-is-no-noise/</link><pubDate>Mon, 09 Aug 2021 00:00:00 +0000</pubDate><guid>https://www.michaelaerni.com/publication/interpolation-can-hurt-robust-generalization-even-when-there-is-no-noise/</guid><description>&lt;p>We presented two related workshop papers:&lt;/p>
&lt;ul>
&lt;li>&lt;a href="https://www.michaelaerni.com/publication/surprising-benefits-of-ridge-regularization-for-noiseless-regression/">Surprising benefits of ridge regularization for noiseless regression&lt;/a> in ICML 2021 Workshop on Overparameterization: Pitfalls and Opportunities&lt;/li>
&lt;li>&lt;a href="https://www.michaelaerni.com/publication/maximizing-the-robust-margin-provably-overfits-on-noiseless-data/">Maximizing the robust margin provably overfits on noiseless data&lt;/a> in ICML 2021 Workshop on Adversarial Machine Learning&lt;/li>
&lt;/ul></description></item></channel></rss>