000201842 001__ 201842
000201842 005__ 20190317000010.0
000201842 037__ $$aCONF
000201842 245__ $$aConstrained convex minimization via model-based excessive gap
000201842 269__ $$a2014
000201842 260__ $$c2014
000201842 336__ $$aConference Papers
000201842 520__ $$aWe introduce a model-based excessive gap technique to analyze first-order primal- dual methods for constrained convex minimization. As a result, we construct new primal-dual methods with optimal convergence rates on the objective residual and the primal feasibility gap of their iterates separately. Through a dual smoothing and prox-function selection strategy, our framework subsumes the augmented Lagrangian, and alternating methods as special cases, where our rates apply.
000201842 6531_ $$aPrimal-dual method
000201842 6531_ $$aexcessive gap technique
000201842 6531_ $$aconstrained convex optimization
000201842 700__ $$0246937$$g229780$$aTran Dinh, Quoc
000201842 700__ $$aCevher, Volkan$$g199128$$0243957
000201842 7112_ $$dDecember 8-11, 2014$$cMontreal, Quebec, Canada$$aAdvances in Neural Information Processing Systems (NIPS) 2014
000201842 8564_ $$uhttps://infoscience.epfl.ch/record/201842/files/NIPS2014-EG-506_TranDinhCevher.pdf$$zPublisher's version$$s452160$$yPublisher's version
000201842 909C0 $$xU12179$$0252306$$pLIONS
000201842 909CO $$qGLOBAL_SET$$pconf$$ooai:infoscience.tind.io:201842$$pSTI
000201842 917Z8 $$x231598
000201842 917Z8 $$x229780
000201842 917Z8 $$x231598
000201842 917Z8 $$x199128
000201842 917Z8 $$x229780
000201842 917Z8 $$x229780
000201842 937__ $$aEPFL-CONF-201842
000201842 973__ $$rREVIEWED$$sACCEPTED$$aEPFL
000201842 980__ $$aCONF