Coresets for polytope distance

72 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Block-Coordinate Frank-Wolfe Optimization for Structural SVMs (2012, methodology): “Interestingly, for structural SVMs we also show that existing batch subgradient and cutting-plane methods are special cases of Frank-Wolfe algorithms, and this leads to stronger and simpler O(1/ε) convergence rate guarantees for these existing algorithms. ar X iv :1 20 7.”
An Equivalence between the Lasso and Support Vector Machines (2013, background): “Any such attained margin value in (4) for some Ax = w directly gives a certiﬁcate on the duality gap as the diﬀerence from the corresponding value k Ax k in problem (1), making this quantity a useful stopping criterion for SVM optimizers, see e.g. (G¨artner & Jaggi, 2009; Clarkson et al., 2010).”
A novel Frank-Wolfe algorithm. Analysis and applications to large-scale SVM training (2013, methodology): “All these methods are nowadays identified as variants of a general approximation procedure for maximizing a differentiable concave function on the simplex, which traces back to Frank and Wolfe [23, 62, 27] and has been recently analyzed by Clarkson [13] and Jaggi [33] under a modern perspective.”
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization (2013, methodology): “For optimizing over the simplex , this trade-off was also described by (Gärtner & Jaggi, 2009; Clarkson, 2010), and by (Shalev-Shwartz et al., 2010) for the 1 -ball (considering primal error).”