BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Bartolomeo Stellato (MIT)
DTSTART:20200609T230000Z
DTEND:20200610T001500Z
DTSTAMP:20260423T024446Z
UID:MADDD/7
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/MADDD/7/">A 
 machine learning approach to optimization</a>\nby Bartolomeo Stellato (MIT
 ) as part of Mathematics of Data and Decisions @ Davis\n\n\nAbstract\nMost
  applications in engineering\, operations research and finance rely on sol
 ving the same optimization problem several times with varying parameters. 
 This method generates a large amount of data that is usually discarded. In
  this talk\, we describe how to use historical data to understand and solv
 e optimization problems. We present a machine learning approach to predict
  the strategy behind the optimal solution of continuous and mixed-integer 
 convex optimization problems. Using interpretable algorithms such as optim
 al classification trees we gain insights on the relationship between the p
 roblem data and the optimal solution. In this way\, optimization is no lon
 ger a black-box and practitioners can understand it. Moreover\, our method
  is able to compute the optimal solutions at very high speed. This applies
  also to non-interpretable machine learning predictors such as neural netw
 orks since they can be evaluated very efficiently. We benchmark our approa
 ch on several examples obtaining accuracy above 90% and computation times 
 multiple orders of magnitude faster than state-of-the-art solvers. Therefo
 re\, our method provides on the one hand a novel insightful understanding 
 of the optimal strategies to solve a broad class of continuous and mixed-i
 nteger optimization problems and on the other hand a powerful computationa
 l tool to solve online optimization at very high speed.\n
LOCATION:https://researchseminars.org/talk/MADDD/7/
END:VEVENT
END:VCALENDAR