[Sds-seminars] 4/27 FDS Seminar: “Entry-wise dissipation for singular vector perturbation bounds”

[Hau, Emily]

[Graphical user interface, text, application  Description automatically generated]

Foundations of Data Science Seminar:

“Entry-wise dissipation for singular vector perturbation bounds”



Speaker: Abhinav Bhardwaj
Yale Mathematics



Thursday, April 27, 2023, 4:00 - 5:00 pm



Location: 24 Hillhouse Avenue, Room 107. In-person only.



Add To: Google Calendar<https://calendar.google.com/calendar/r/eventedit?text=FDS+Seminar%3A+Abhinav+Bhardwaj+%28Yale+Math%29%2C+%26%238220%3BEntry-wise+dissipation+for+singular+vector+perturbation+bounds%26%238221%3B&details=Speaker%3A+Abhinav+Bhardwaj+%28Yale+Math%29+Abstract%3A+Consider+a+random+perturbation+of+a+low+rank+matrix.+In+this+talk%2C+we+discuss+entry-wise+bounds+on+the+perturbation+of+the+singular+vectors+%28i.e%2C+a+Davis-Kahan+type+bound+in+the+infinity+norm%29.+Among+others%2C+our+result+shows+that%2C+under+common+incoherence+assumptions%2C+the+entry-wise+error+is+evenly+dissipated.+This%26hellip%3B+%3Ca+class%3D%22continue%22+href%3D%22https%3A%2F%2Ffds.yale.edu%2Fcalendar_event%2Ffds-seminar-entry-wise-dissipation-for-singular-vector-perturbation-bounds%2F%22%3Econtinue+reading%3Cspan%3E+FDS+Seminar%3A+Abhinav+Bhardwaj+%28Yale+Math%29%2C+%26%238220%3BEntry-wise+dissipation+for+singular+vector+perturbation+bounds%26%238221%3B%3C%2Fspan%3E%3C%2Fa%3E...&location&dates=20230427T200000Z/20230427T210000Z> | Outlook<https://fds.yale.edu/wp-admin/admin-ajax.php?event=1104&action=download_ical_file> | iCal File<https://fds.yale.edu/wp-admin/admin-ajax.php?event=1104&action=download_ical_file>



Abstract: Consider a random perturbation of a low rank matrix. In this talk, we discuss entry-wise bounds on the perturbation of the singular vectors (i.e, a Davis-Kahan type bound in the infinity norm). Among others, our result shows that, under common incoherence assumptions, the entry-wise error is evenly dissipated. This improves a number of previous results and has algorithmic applications for many well known clustering problems, including the hidden clique, planted coloring, and planted bipartition.



Upcoming:

April 24: FDS Colloquium, Robert Schapire (Microsoft Research) “Convex Analysis at Infinity: An Introduction to Astral Space”<https://fds.yale.edu/calendar_event/fds-colloquium-schapire/>

May 1: Workshop: Healthcare Data Science (registration required)<https://fds.yale.edu/calendar_event/data-science-for-healthcare/>

May 3: FDS Seminar, Wei Ji Ma<https://fds.yale.edu/calendar_event/fds-seminar-weiji-ma/>


Emily E. H. Hau | Associate Director, Data Science @ Yale University
Yale Institute for Foundations of Data Science (FDS)
Yale Institute for Network Science (YINS)
17 Hillhouse Avenue | Room 341 | New Haven, CT 06511
emily.hau at yale.edu<mailto:emily.hau at yale.edu> | P: 203-436-4732
@yaledatascience @YINSedge @EmilyDeeganHau

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20230424/d6f52163/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 22230 bytes
Desc: image001.png
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20230424/d6f52163/attachment.png>