BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Madrid BEGIN:DAYLIGHT DTSTART:20240331T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20241027T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240705T120330Z UID:599F9A75-A9C2-48DB-ADD8-89644BF66326 DTSTART;TZID=Europe/Madrid:20240702T111500 DTEND;TZID=Europe/Madrid:20240702T123000 DESCRIPTION:On Tuesday\, July 2nd\, Prof. Anand Sarwate from Rutgers Univer sity give his Distinguished Lecture:\n\nTitle: "Learning with Structured T ensor Decompositions”\n\nAbstract: Many measurements or signals are mult idimensional\, or tensor-valued. Vectorizing tensor data for statistical a nd machine learning tasks often results in having to fit a very large numb er of parameters. Using tensor decompositions to model such data can give a flexible and useful modeling framework whose complexity can adapt to the amount of data available. This talk will introduce classical decompositio ns (CP\, Tucker) as well as more recent ones (tensor train\, block tensor decomposition\, and low separation rank) and show how they can be used to learn scalable representations for tensor-valued data and make predictions from tensor-valued data. Time permitting\, we will describe applications in federated learning as well as open problems for future research.\n\nThe event will be transmitted via Teams: [link](https://teams.microsoft.com/l /meetup-join/19%3ameeting_MTgzMjdkYjUtZDYxNi00NmUxLTk0YjAtNDQwZTIxYWQzMDdh %40thread.v2/0?context=%7b%22Tid%22%3a%225f84c4ea-370d-4b9e-830c-756f8bf1b 51f%22%2c%22Oid%22%3a%22b4bdccba-f532-48cd-8208-457d6bc3086c%22%7d)\n\nCo- sponsored by: Universidad Rey Juan Carlos\, Universidad Carlos III de Madr id\n\nSpeaker(s): Dr. Anand Sarwate\, \n\nVirtual: https://events.vtools.i eee.org/m/425691 LOCATION:Virtual: https://events.vtools.ieee.org/m/425691 ORGANIZER:grace.villacres@urjc.es SEQUENCE:14 SUMMARY:IEEE Distinguished Lecture by Anand Sarwate (Rutgers University) URL;VALUE=URI:https://events.vtools.ieee.org/m/425691 X-ALT-DESC:Description: <br /><p class="MsoNormal"><span lang="EN-GB">On Tu esday\, July 2nd\, Prof. Anand Sarwate from Rutgers University give his Di stinguished Lecture:&nbsp\;</span></p>\n<p class="MsoNormal"><span lang="E N-GB"><strong>Title: "Learning with Structured Tensor Decompositions&rdquo \;</strong></span></p>\n<p class="MsoNormal"><span lang="EN-GB"><strong>Ab stract: </strong>Many measurements or signals are multidimensional\, or te nsor-valued. Vectorizing tensor data for statistical and machine learning tasks often results in having to fit a very large number of parameters. Us ing tensor decompositions to model such data can give a flexible and usefu l modeling framework whose complexity can adapt to the amount of data avai lable. This talk will introduce classical decompositions (CP\, Tucker) as well as more recent ones (tensor train\, block tensor decomposition\, and low separation rank) and show how they can be used to learn scalable repre sentations for tensor-valued data and make predictions from tensor-valued data. Time permitting\, we will describe applications in federated learnin g as well as open problems for future research.</span></p>\n<p class="MsoN ormal">&nbsp\;</p>\n<p class="MsoNormal"><span lang="EN-GB">The event will be transmitted via Teams: <a href="https://teams.microsoft.com/l/meetup-j oin/19%3ameeting_MTgzMjdkYjUtZDYxNi00NmUxLTk0YjAtNDQwZTIxYWQzMDdh%40thread .v2/0?context=%7b%22Tid%22%3a%225f84c4ea-370d-4b9e-830c-756f8bf1b51f%22%2c %22Oid%22%3a%22b4bdccba-f532-48cd-8208-457d6bc3086c%22%7d">link</a></span> </p> END:VEVENT END:VCALENDAR