<div dir="ltr"><br><div class="gmail_quote"><br><br><div dir="ltr"><br><div><p class="MsoNormal" style="line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><b><span lang="EN-US" style="font-size:12pt;line-height:115%">Probability Seminar - IM-UFRJ </span></b></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%"> </span></p>
<p class="MsoNormal" style="line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Dear
colleagues, </span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%"> </span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Our next seminar will be held on Monday, <b>March 7, </b> from <b>3 p.m. to 4 p.m</b>. (Rio de Janeiro
local time).</span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">We will be using the platform Zoom and the link is:</span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><a href="https://us02web.zoom.us/j/83698166702?pwd=ejFxYmh3dVk5b3J3SG0wMWxEVnVrUT09" style="color:blue" target="_blank"><span lang="EN-US" style="font-size:12pt;line-height:115%;color:rgb(17,85,204);background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">https://us02web.zoom.us/j/83698166702?pwd=ejFxYmh3dVk5b3J3SG0wMWxEVnVrUT09</span></a><span lang="EN-US" style="font-size:12pt;line-height:115%"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Speaker: </span><strong><span lang="EN-US" style="font-size:12pt;line-height:115%;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">Guilherme
Ost (IM-UFRJ)</span></strong><b><span lang="EN-US" style="font-size:12pt;line-height:115%"></span></b></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Title:
</span><b><span lang="EN-US" style="font-size:12pt;line-height:115%;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">Sparse Markov
Models for High-dimensional Inference</span></b><b><span lang="EN-US" style="font-size:12pt;line-height:115%;color:black;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"></span></b></p>
<p class="MsoNormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial;margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Abstract: </span><span lang="EN-US" style="font-size:12pt;line-height:115%"> </span><span lang="EN-US" style="font-size:12pt;line-height:115%;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">Finite order Markov models are theoretically
well-studied models for dependent categorical data. Despite their generality,
application in empirical work when the order is larger than one is quite rare.
Practitioners avoid using higher order Markov models because (1) the number of
parameters grows exponentially with the order, (2) the interpretation is often
difficult. Mixture of transition distribution models (MTD) were introduced to
overcome both limitations. MTD represent higher order Markov models
as a convex mixture of single step Markov chains, reducing the number of
parameters and increasing the interpretability. Nevertheless, in practice,
estimation of MTD models with large orders is still limited because
of the curse of dimensionality and high algorithm complexity. Here,
we prove that if only few lags are relevant we can consistently and efficiently
recover the lags and estimate the transition probabilities of high
order MTD models. The key innovation is a recursive procedure
for the selection of the relevant lags of the model. Our results are based on
(1) a new structural result of the MTD and (2) an improved martingale
concentration inequality. Our theoretical results are illustrated through
simulations. </span></p>
<p class="MsoNormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial;margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">This is a joint work with Daniel Y. Takahashi
(Ice/UFRN).</span></p>
<p class="MsoNormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial;margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%;color:black"> </span></p>
<p class="MsoNormal" style="line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">All the talks
are held in English. </span></p>
<p class="MsoNormal" style="line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">More complete
information about the seminars will be available at </span></p>
<p class="MsoNormal" style="line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%"><a href="http://www.dme.ufrj.br/?page_id=2438" target="_blank">http://www.dme.ufrj.br/?page_id=2438</a></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Those who do not wish to receive our next
announcements may simply send an email to <<a href="mailto:eulalia@im.ufrj.br" target="_blank">eulalia@im.ufrj.br</a>> asking to be removed from the list. </span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Thanks for circulating this information. </span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Sincerely, </span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%">Organizers: Giulio Iacobelli and Maria Eulalia Vares</span></p>
<p class="MsoNormal" style="margin:0cm 0cm 10pt;line-height:115%;font-size:11pt;font-family:Calibri,"sans-serif""><span lang="EN-US" style="font-size:12pt;line-height:115%"><br>
<br>
<br>
</span></p></div></div><div id="m_4940443855317596953DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2"><br> <table style="border-top:1px solid #d3d4de">
<tbody><tr>
<td style="width:55px;padding-top:18px"><a href="https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail" target="_blank"><img src="https://ipmcdn.avast.com/images/icons/icon-envelope-tick-round-orange-animated-no-repeat-v1.gif" alt="" width="46" height="29" style="width:46px;height:29px"></a></td>
<td style="width:470px;padding-top:17px;color:#41424e;font-size:13px;font-family:Arial,Helvetica,sans-serif;line-height:18px">Livre de vírus. <a href="https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail" style="color:#4453ea" target="_blank">www.avast.com</a>. </td>
</tr>
</tbody></table>
<a href="#m_4940443855317596953_DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2" width="1" height="1"></a></div>
</div></div>