BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//prima-2022//speaker calendar//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZOME
TZID:America/Vancouver
TZURL:http://tzurl.org/zoneinfo-outlook/America/Vancouver
X-LIC-LOCATION:America/Vancouver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP;TZID=America/Vancouver:20221205T114500
DTSTART;TZID=America/Vancouver:20221205T114500
DTEND;TZID=America/Vancouver:20221205T120500

UID:20221205T114500@prima2022.primamath.org
SUMMARY:Adversarial training and the generalized Wasserstein barycenter problem
DESCRIPTION:Adversarial training is a framework widely used by practitioners to enforce robustness of machine learning models.  During the training process, the learner is pitted against an adversary who has the power to alter the input data.  As a result, the learner is forced to build a model that is robust to data perturbations.  Despite the importance and relative conceptual simplicity of adversarial training, there are many aspects that are still not well-understood (e.g. regularization effects, geometric/analytic interpretations, tradeoff between accuracy and robustness, etc...), particularly in the case of multiclass classification. 

In this talk, I will show that in the non-parametric setting, the adversarial training problem is equivalent to a generalized version of the Wasserstein barycenter problem.  The connection between these problems allows us to completely characterize the optimal adversarial strategy and to bring in tools from optimal transport to analyze and compute optimal classifiers.  This also has implications for the parametric setting, as the value of the generalized barycenter problem gives a universal upper bound on the robustness/accuracy tradeoff inherent to adversarial training. 


Joint work with Nicolas Garcia Trillos and Jakwang Kim.

STATUS:CONFIRMED
LOCATION:Port Alberni
END:VEVENT
END:VCALENDAR