Optimistic robust optimization with applications to machine learning
MetadataShow full item record
Robust Optimization has traditionally taken a pessimistic, or worst-case viewpoint of uncertainty which is motivated by a desire to find sets of optimal policies that maintain feasibility under a variety of operating conditions. In this paper, we explore an optimistic, or best-case view of uncertainty and show that it can be a fruitful approach. We show that these techniques can be used to address a wide variety of problems. First, we apply our methods in the context of robust linear programming, providing a method for reducing conservatism in intuitive ways that encode economically realistic modeling assumptions. Second, we look at problems in machine learning and find that this approach is strongly connected to the existing literature. Specifically, we provide a new interpretation for popular sparsity inducing non-convex regularization schemes. Additionally, we show that successful approaches for dealing with outliers and noise can be interpreted as optimistic robust optimization problems. Although many of the problems resulting from our approach are non-convex, we find that DCA or DCA-like optimization approaches can be intuitive and e fficient.
Showing items related by title, author, creator and subject.
Kilic, Sedat (Monterey, California: Naval Postgraduate School, 2016-12);East Asia is an important region for global stability. Major economies—China, Japan, and South Korea—are located in the region. The phenomenon of a rising China, the response of the United States to a rising China, and the ...
Lewis, Chantee (Monterey, California : Naval Postgraduate School, 1964);On 17 January 1962, Executive Order 10988 (Employee-Management Cooperation in the Federal Service) ushered the Federal manager (both military and civilian) into a new era of employee-management relations. The unknown ...
Collins, Arthur (Monterey, California. Naval Postgraduate School, 2001-06);Russia's Kaliningrad Oblast (Region) has a history of being terra incognita. In defiance of geographic and historical realities, the Allied leaders of World War II carved the oblast from the northern third of East Prussia ...