This algorithm can not only avoid evaluating the exact full gradient which can be expensive in big data models but also weaken the stringent global Lipschitz gradient continuity assumption on the smooth part of the problem. However, under the nonconvex case, there is few analysis on the ...
John C. Duchi,R Feng - 《Siam Journal on Optimization》 被引量: 40发表: 2017年 Stochastic Frank-Wolfe Methods for Nonconvex Optimization We study Frank-Wolfe methods for nonconvex stochastic and finite-sum optimization problems. Frank-Wolfe methods (in the convex case) have gained tremendous.....
Nesterov, Y.: A method for unconstrained convex minimization problem with the rate of convergence o (1/k\(^{2}\)). Dokl. SSSR 269, 543–547 (1983) Google Scholar Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, Berlin (2004) Book Google...
Solving (most) of a set of quadratic equalities: Composite optimization\n for robust phase retrieval We develop procedures, based on minimization of the composition $f(x) =h(c(x))$ of a convex function $h$ and smooth function $c$, for solving randomcollect... Duchi John C,R Feng - ...
Although S2L is also based on scribble annotations, they focus on cell segmentation, which is different from our problem. The core idea of S2L is to combine pseudo-labeling with label filtering to generate reliable labels from weak supervision, while our method filters out the unreliable ...
The MIL strategy results in a non-convex optimization problem; in practice, solvers tend to get stuck in local optima such that the quality of the solution strongly depends on the initialization. developing various initialization strategies [19, 5, 32, 4] ...
An important approach in multiple criteria linear programming is the optimization of some function over the efficient or weakly-efficient set. This is a very difficult nonconvex optimization problem, even for the case that the function to be optimized is linear. In this article we consider the pr...
M Schweighofer - 《Siam Journal on Optimization》 被引量: 261发表: 2005年 Sparsity-Exploiting Moment-Based Relaxations of the Optimal Power Flow Problem Convex relaxations of non-convex optimal power flow (OPF) problems have recently attracted significant interest. While existing relaxations globally so...
optimizationIn this article, we present a conjugate duality for nonconvex optimization problems. This duality scheme is symmetric and has zero gap. As applied to a vector-maximization problem, it transforms the latter into an optimization problem over a weakly efficient set which can be solved by...
This approach was extended in [13] to include generic linear constraints on the label space, by formulating label prediction as a convex optimization problem. Both these methods showed excellent results on the VOC 2012 dataset, but are sensitive to the linear/cardinality constraints. We address ...