<html>
  <head>

    <meta http-equiv="content-type" content="text/html; charset=UTF-8">
  </head>
  <body text="#000000" bgcolor="#FFFFFF">
    <p>Καλημέρα,</p>
    <p>Τη Τετάρτη 10/7, στις 14:30 στο Αμφιθέατρο Πολυμέσων της
      Κεντρικής Βιβλιοθήκης, έχουμε τη χαρά να φιλοξενούμε την ομιλία
      της Βάσιας Καλαβρή, ερευνήτριας στο ETH. Στη συνέχεια μπορείτε να
      βρείτε λεπτομέρειες της ομιλίας και βιογραφικό της ομιλήτριας.</p>
    <p>Χαιρετισμους,</p>
    <p>Γιώργος Γκούμας</p>
    <p><span
        id="gmail-docs-internal-guid-4b4b4dc5-7fff-0a19-1969-007359d5096e">
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Title: Long-running data stream analytics at scale</span></p>
        <br>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Abstract</span></p>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">—————</span></p>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">While the early wave of big data technologies focused largely on accommodating the scale and complexity of available information, emerging data-driven applications additionally require low-latency and continuously updated results. Stream processing renounces the traditional view of static data inputs and instead advocates for long-running analysis of possibly unbounded event streams.</span></p>
        <br>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">In this talk, I discuss fundamental research challenges in building next-generation streaming systems capable of automatic re-configuration without downtime. I will share recent work on an automatic scaling controller which makes fast and accurate scaling decisions via lightweight runtime instrumentation and a comprehensive dataflow performance model. I will conclude with open problems and future directions in automatic, long-running operation of streaming computations and large-scale continuous data analytics in general.</span></p>
        <br>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Bio</span></p>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">—————</span></p>
        <p dir="ltr"
          style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Vasiliki (Vasia) Kalavri is a postdoctoral fellow at the Systems Group of ETH Zurich and an Adjunct Assistant Professor in the Department of Computer Science at Boston University. Her research interests include distributed stream processing, large-scale graph analytics, and the intersection of the two. Vasia has a joint PhD from KTH, Stockholm, and UCLouvain, Belgium, where she was an EMJD-DC fellow. Her PhD thesis received the IBM Innovation Award 2017. Vasia is also a PMC member of Apache Flink and co-author of O’Reilly’s “Stream Processing with Apache Flink”.</span></p>
      </span></p>
    <pre class="moz-signature" cols="72">-- 
Georgios I. Goumas
Assistant Professor
National Technical University of Athens
Computing Systems Laboratory
Tel. +30-210-7722402
e-mail: <a class="moz-txt-link-abbreviated" href="mailto:goumas@cslab.ece.ntua.gr">goumas@cslab.ece.ntua.gr</a>
<a class="moz-txt-link-freetext" href="http://www.cslab.ece.ntua.gr/~goumas">http://www.cslab.ece.ntua.gr/~goumas</a></pre>
  </body>
</html>