BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Ahmadreza Marandi (UBC-O hosted) (Eindhoven University) DTSTART:20240828T210000Z DTEND:20240828T220000Z DTSTAMP:20260513T193638Z UID:SFUOR/38 DESCRIPTION:Title: A Clustering-based uncertainty set for Robust Optimization\nby Ahmadrez a Marandi (UBC-O hosted) (Eindhoven University) as part of PIMS-CORDS SFU Operations Research Seminar\n\nLecture held in ASB 10908.\n\nAbstract\nRob ust Optimization (RO) is an approach to tackle uncertainties in the parame ters of an optimization\nproblem. Constructing an uncertainty set is cruci al for RO\, as it determines the quality and the\nconservativeness of the solutions. In this talk\, we introduce an approach for constructing a data -driven\nuncertainty set through volume-based clustering\, which we call M inimum-Volume Norm-Based\nClustering (MVNBC)\, that leads to less conserva tive solutions. MVNBC extends the concept of\nMinimum-Volume Ellipsoid Clu stering by enabling customizable regions containing clusters. These\nregio ns are defined based on a given set of vector norms\, hence providing grea t flexibility in capturing\ndiverse data patterns. We formulate a mixed-in teger conic optimization problem for MVNBC. To\naddress computational comp lexities\, we design an efficient iterative approximation algorithm where we\nreassign points to clusters and improve the volume of the regions. Our numerical experiments\ndemonstrate the effectiveness of our approach in c apturing data patterns and finding clusters with\nminimum total volume. Mo reover\, constructed uncertainty sets based on MVNBC result in robust\nsol utions with 10% improvement in the objective value compared to the ones ob tained by a recent datadriven\nuncertainty set. Therefore\, using our unce rtainty sets in RO problems can generate less\nconservative solutions comp ared to traditional uncertainty sets as well as other existing data-driven \napproaches.\n LOCATION:https://researchseminars.org/talk/SFUOR/38/ END:VEVENT END:VCALENDAR