A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1810.10132v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Smoothed Online Optimization for Regression and Control
[article]
<span title="2019-04-04">2019</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2018-10-23">2018</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.10132v1">arXiv:1810.10132v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qqn5aaxmtfd6tlhnb4blq6mxmy">fatcat:qqn5aaxmtfd6tlhnb4blq6mxmy</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.10132v1">arXiv:1810.10132v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qqn5aaxmtfd6tlhnb4blq6mxmy">fatcat:qqn5aaxmtfd6tlhnb4blq6mxmy</a> </span>
We consider Online Convex Optimization (OCO) in the setting where the costs are m-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive ratio 3 + O(1/m), irrespective of the ambient dimension. Additionally, we show that when the sequence of cost functions is ϵ-smooth, OBD has near-optimal dynamic regret and maintains
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.10132v2">arXiv:1810.10132v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wmglvcrpsff2beqx4cl662hyra">fatcat:wmglvcrpsff2beqx4cl662hyra</a>
</span>
more »
... rong per-round accuracy. We demonstrate the generality of our approach by showing that the OBD framework can be used to construct competitive algorithms for a variety of online problems across learning and control, including online variants of ridge regression, logistic regression, maximum likelihood estimation, and LQR control.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200920093040/https://arxiv.org/pdf/1810.10132v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/0a/db/0adb799f829f6454b3cc812edebad283af11e412.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.10132v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>