Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950425460> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2950425460 abstract "In this paper we propose a framework for solving constrained online convex optimization problem. Our motivation stems from the observation that most algorithms proposed for online convex optimization require a projection onto the convex set $mathcal{K}$ from which the decisions are made. While for simple shapes (e.g. Euclidean ball) the projection is straightforward, for arbitrary complex sets this is the main computational challenge and may be inefficient in practice. In this paper, we consider an alternative online convex optimization problem. Instead of requiring decisions belong to $mathcal{K}$ for all rounds, we only require that the constraints which define the set $mathcal{K}$ be satisfied in the long run. We show that our framework can be utilized to solve a relaxed version of online learning with side constraints addressed in cite{DBLP:conf/colt/MannorT06} and cite{DBLP:conf/aaai/KvetonYTM08}. By turning the problem into an online convex-concave optimization problem, we propose an efficient algorithm which achieves $tilde{mathcal{O}}(sqrt{T})$ regret bound and $tilde{mathcal{O}}(T^{3/4})$ bound for the violation of constraints. Then we modify the algorithm in order to guarantee that the constraints are satisfied in the long run. This gain is achieved at the price of getting $tilde{mathcal{O}}(T^{3/4})$ regret bound. Our second algorithm is based on the Mirror Prox method citep{nemirovski-2005-prox} to solve variational inequalities which achieves $tilde{mathcal{mathcal{O}}}(T^{2/3})$ bound for both regret and the violation of constraints when the domain $K$ can be described by a finite number of linear constraints. Finally, we extend the result to the setting where we only have partial access to the convex set $mathcal{K}$ and propose a multipoint bandit feedback algorithm with the same bounds in expectation as our first algorithm." @default.
- W2950425460 created "2019-06-27" @default.
- W2950425460 creator A5023288846 @default.
- W2950425460 creator A5069394608 @default.
- W2950425460 creator A5076083402 @default.
- W2950425460 date "2011-11-25" @default.
- W2950425460 modified "2023-09-27" @default.
- W2950425460 title "Trading Regret for Efficiency: Online Convex Optimization with Long Term Constraints" @default.
- W2950425460 cites W153281708 @default.
- W2950425460 cites W1545471058 @default.
- W2950425460 cites W1583497301 @default.
- W2950425460 cites W1978259121 @default.
- W2950425460 cites W2004001705 @default.
- W2950425460 cites W2014482607 @default.
- W2950425460 cites W2089559088 @default.
- W2950425460 cites W2095762034 @default.
- W2950425460 cites W2109339818 @default.
- W2950425460 cites W2110947625 @default.
- W2950425460 cites W2120745256 @default.
- W2950425460 cites W2129160848 @default.
- W2950425460 cites W2145630740 @default.
- W2950425460 cites W2296319761 @default.
- W2950425460 cites W2963138632 @default.
- W2950425460 hasPublicationYear "2011" @default.
- W2950425460 type Work @default.
- W2950425460 sameAs 2950425460 @default.
- W2950425460 citedByCount "0" @default.
- W2950425460 crossrefType "posted-content" @default.
- W2950425460 hasAuthorship W2950425460A5023288846 @default.
- W2950425460 hasAuthorship W2950425460A5069394608 @default.
- W2950425460 hasAuthorship W2950425460A5076083402 @default.
- W2950425460 hasConcept C105795698 @default.
- W2950425460 hasConcept C112680207 @default.
- W2950425460 hasConcept C11413529 @default.
- W2950425460 hasConcept C114614502 @default.
- W2950425460 hasConcept C118615104 @default.
- W2950425460 hasConcept C126255220 @default.
- W2950425460 hasConcept C134306372 @default.
- W2950425460 hasConcept C137836250 @default.
- W2950425460 hasConcept C157972887 @default.
- W2950425460 hasConcept C177264268 @default.
- W2950425460 hasConcept C196921405 @default.
- W2950425460 hasConcept C199360897 @default.
- W2950425460 hasConcept C2524010 @default.
- W2950425460 hasConcept C33923547 @default.
- W2950425460 hasConcept C36686422 @default.
- W2950425460 hasConcept C41008148 @default.
- W2950425460 hasConcept C49870271 @default.
- W2950425460 hasConcept C50817715 @default.
- W2950425460 hasConcept C57493831 @default.
- W2950425460 hasConcept C77553402 @default.
- W2950425460 hasConceptScore W2950425460C105795698 @default.
- W2950425460 hasConceptScore W2950425460C112680207 @default.
- W2950425460 hasConceptScore W2950425460C11413529 @default.
- W2950425460 hasConceptScore W2950425460C114614502 @default.
- W2950425460 hasConceptScore W2950425460C118615104 @default.
- W2950425460 hasConceptScore W2950425460C126255220 @default.
- W2950425460 hasConceptScore W2950425460C134306372 @default.
- W2950425460 hasConceptScore W2950425460C137836250 @default.
- W2950425460 hasConceptScore W2950425460C157972887 @default.
- W2950425460 hasConceptScore W2950425460C177264268 @default.
- W2950425460 hasConceptScore W2950425460C196921405 @default.
- W2950425460 hasConceptScore W2950425460C199360897 @default.
- W2950425460 hasConceptScore W2950425460C2524010 @default.
- W2950425460 hasConceptScore W2950425460C33923547 @default.
- W2950425460 hasConceptScore W2950425460C36686422 @default.
- W2950425460 hasConceptScore W2950425460C41008148 @default.
- W2950425460 hasConceptScore W2950425460C49870271 @default.
- W2950425460 hasConceptScore W2950425460C50817715 @default.
- W2950425460 hasConceptScore W2950425460C57493831 @default.
- W2950425460 hasConceptScore W2950425460C77553402 @default.
- W2950425460 hasLocation W29504254601 @default.
- W2950425460 hasOpenAccess W2950425460 @default.
- W2950425460 hasPrimaryLocation W29504254601 @default.
- W2950425460 hasRelatedWork W1543275501 @default.
- W2950425460 hasRelatedWork W1569599893 @default.
- W2950425460 hasRelatedWork W1816320414 @default.
- W2950425460 hasRelatedWork W2056156243 @default.
- W2950425460 hasRelatedWork W2073322025 @default.
- W2950425460 hasRelatedWork W2163020700 @default.
- W2950425460 hasRelatedWork W2468229791 @default.
- W2950425460 hasRelatedWork W2906305178 @default.
- W2950425460 hasRelatedWork W292627938 @default.
- W2950425460 hasRelatedWork W2950524127 @default.
- W2950425460 hasRelatedWork W2951929842 @default.
- W2950425460 hasRelatedWork W2955073010 @default.
- W2950425460 hasRelatedWork W2963410920 @default.
- W2950425460 hasRelatedWork W2965600716 @default.
- W2950425460 hasRelatedWork W3034813188 @default.
- W2950425460 hasRelatedWork W3038062406 @default.
- W2950425460 hasRelatedWork W3090913015 @default.
- W2950425460 hasRelatedWork W3205187894 @default.
- W2950425460 hasRelatedWork W60640206 @default.
- W2950425460 hasRelatedWork W3174537292 @default.
- W2950425460 isParatext "false" @default.
- W2950425460 isRetracted "false" @default.
- W2950425460 magId "2950425460" @default.
- W2950425460 workType "article" @default.