linear manifold/ C1180 Optimisation techniques C1160 Combinatorial mathematicsA lineraly constrained global optimization problem is studied, where the objective function is the saum of a convex function g(x)a nd a nonconvex function f(x) satisfying a rank two condition. Roughly speaking, the ...
Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter By Zeyuan Allen-Zhu 2017, Carmon- Duchi-Hinder-Sidford, "Convex Until Proven Guilty": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions By Yair Carmon, John C. Duchi, Oliver Hinder and Aaron...
optimisationresource allocation/ global optimization problemsseparable nonconvex objective functionlinear constraintmaximizationheuristic algorithmupper boundconcave relaxation problemoptimal resource distributionFor a class of global optimization (maximization) problems, with a separable non-concave objective function ...
J. F. TOLAND, "A Duality Principle for Non-Convex Optimisation and the calculus of Variations," University of Essex Fluid Mechanics Research Institute Report No. 77, November 1976, Archiv. Rational Me&. Analysis (in press).J. Toland, A duality principle for non-convex optimisation and the ...
non-convex optimisation: cma-es with gradients Huajian Qiu April 2020 Introduction In this project, I work on improving a global optimisation method-covariance matrix adaptation evolution strategy(CMA-ES) by exploitingdifferentiablity. In short, CMA-ES is very likely the most successful evolution stra...
signSGD: Compressed optimisation for non-convex problemsproceedings.mlr.press/v80/bernstein18a 这篇论文发表在 ICML 2018上,主要探讨了关于通信梯度的符号位的 SGD 方法——SignSGD。该方法被用来解决在大规模分布式机器学习中对于梯度的频繁且大量的通信造成的性能瓶颈问题。第一个提出使用基于符号的方法的是 RPR...
Esaim Control Optimisation & Calculus of VariationsR.I. Bo¸t, E.R. Csetnek, A forward-backward dynamical approach to the minimization of the sum of a nonsmooth convex with a smooth nonconvex function, to appear in ESAIM: Control, Optimisation and Calculus of Variations, arXiv:1507.01416,...
global optimisation problem, and therefore likely to be NP-hard (see, e.g., [118, 124]). In fact, the situation is worse than this. Several simple cases of non-convex MINLP, including the case in which all functions are quadratic, all variables are integer-constrained, and the number ...
In this paper, we address the nonconvex optimization problem, with the goal function and the inequality constraints given by the functions represented by the difference of convex functions. The effectiveness of the classical Lagrange function and the max-merit function is being investigated as the me...
In this paper, we consider the asynchronous training problem with the non-convex case. We theoretically study this problem to find an approximating second-order stationary point using asynchronous algorithms in non-convex optimization and investigate the behaviors of APSGD near-saddle points. This ...