We consider a recently proposed optimization formulation of multi-task learning based on trace norm regularized least squares. While this problem may be formulated as a semidefini...
Ting Kei Pong, Paul Tseng, Shuiwang Ji, Jieping Ye
Using duality, we reformulate the asymmetric variational inequality (VI) problem over a conic region as an optimization problem. We give sufficient conditions for the convexity of...
We describe a primal-dual framework for the design and analysis of online strongly convex optimization algorithms. Our framework yields the tightest known logarithmic regret bound...
We consider two notions for the representations of convex cones: G-representation and liftedG-representation. The former represents a convex cone as a slice of another; the latter...
Consider a convex relaxation ^f of a pseudo-boolean function f. We say that the relaxation is totally half-integral if ^f(x) is a polyhedral function with halfintegral extreme poi...