Timezone: »

 
Poster
Designing smoothing functions for improved worst-case competitive ratio in online optimization
Reza Eghbali · Maryam Fazel

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #27
in Wednesday Posters »
Online optimization covers problems such as online resource allocation, online bipartite matching, adwords (a central problem in e-commerce and advertising), and adwords with separable concave returns. We analyze the worst case competitive ratio of two primal-dual algorithms for a class of online convex (conic) optimization problems that contains the previous examples as special cases defined on the positive orthant. We derive a sufficient condition on the objective function that guarantees a constant worst case competitive ratio (greater than or equal to $\frac{1}{2}$) for monotone objective functions. We provide new examples of online problems on the positive orthant % and the positive semidefinite cone that satisfy the sufficient condition. We show how smoothing can improve the competitive ratio of these algorithms, and in particular for separable functions, we show that the optimal smoothing can be derived by solving a convex optimization problem. This result allows us to directly optimize the competitive ratio bound over a class of smoothing functions, and hence design effective smoothing customized for a given cost function.
Keywords: Online Learning · Convex Optimization
[ PDF] 

Author Information

Reza Eghbali (University of washington)
Maryam Fazel (University of Washington)

More from the Same Authors