Matches in SemOpenAlex for { <https://semopenalex.org/work/W1876041327> ?p ?o ?g. }
- W1876041327 abstract "A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to combinatorial constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we consider efficient learning in large-scale combinatorial semi-bandits with linear generalization, and as a solution, propose two learning algorithms called Combinatorial Linear Thompson Sampling (CombLinTS) and Combinatorial Linear UCB (CombLinUCB). Both algorithms are computationally efficient as long as the offline version of the combinatorial problem can be solved efficiently. We establish that CombLinTS and CombLinUCB are also provably statistically efficient under reasonable assumptions, by developing regret bounds that are independent of the problem scale (number of items) and sublinear in time. We also evaluate CombLinTS on a variety of problems with thousands of items. Our experiment results demonstrate that CombLinTS is scalable, robust to the choice of algorithm parameters, and significantly outperforms the best of our baselines." @default.
- W1876041327 created "2016-06-24" @default.
- W1876041327 creator A5018753905 @default.
- W1876041327 creator A5049020775 @default.
- W1876041327 creator A5067555437 @default.
- W1876041327 date "2014-06-28" @default.
- W1876041327 modified "2023-09-25" @default.
- W1876041327 title "Efficient Learning in Large-Scale Combinatorial Semi-Bandits" @default.
- W1876041327 cites W1561097743 @default.
- W1876041327 cites W1571154989 @default.
- W1876041327 cites W1900560890 @default.
- W1876041327 cites W1911551976 @default.
- W1876041327 cites W2036536766 @default.
- W1876041327 cites W2039522160 @default.
- W1876041327 cites W2054141820 @default.
- W1876041327 cites W2093562354 @default.
- W1876041327 cites W2108114251 @default.
- W1876041327 cites W2108738385 @default.
- W1876041327 cites W2115044435 @default.
- W1876041327 cites W2117353901 @default.
- W1876041327 cites W2119738618 @default.
- W1876041327 cites W2130488484 @default.
- W1876041327 cites W2149721706 @default.
- W1876041327 cites W2151228446 @default.
- W1876041327 cites W2152898676 @default.
- W1876041327 cites W2166253248 @default.
- W1876041327 cites W2202573872 @default.
- W1876041327 cites W2249990263 @default.
- W1876041327 cites W2275211641 @default.
- W1876041327 cites W2340149117 @default.
- W1876041327 cites W2914156981 @default.
- W1876041327 cites W2962767126 @default.
- W1876041327 cites W2964007796 @default.
- W1876041327 cites W2964326108 @default.
- W1876041327 cites W3120740533 @default.
- W1876041327 cites W35251828 @default.
- W1876041327 cites W50486269 @default.
- W1876041327 doi "https://doi.org/10.48550/arxiv.1406.7443" @default.
- W1876041327 hasPublicationYear "2014" @default.
- W1876041327 type Work @default.
- W1876041327 sameAs 1876041327 @default.
- W1876041327 citedByCount "37" @default.
- W1876041327 countsByYear W18760413272014 @default.
- W1876041327 countsByYear W18760413272015 @default.
- W1876041327 countsByYear W18760413272016 @default.
- W1876041327 countsByYear W18760413272017 @default.
- W1876041327 countsByYear W18760413272018 @default.
- W1876041327 countsByYear W18760413272019 @default.
- W1876041327 countsByYear W18760413272020 @default.
- W1876041327 countsByYear W18760413272021 @default.
- W1876041327 crossrefType "posted-content" @default.
- W1876041327 hasAuthorship W1876041327A5018753905 @default.
- W1876041327 hasAuthorship W1876041327A5049020775 @default.
- W1876041327 hasAuthorship W1876041327A5067555437 @default.
- W1876041327 hasBestOaLocation W18760413271 @default.
- W1876041327 hasConcept C117160843 @default.
- W1876041327 hasConcept C118615104 @default.
- W1876041327 hasConcept C119857082 @default.
- W1876041327 hasConcept C121332964 @default.
- W1876041327 hasConcept C126255220 @default.
- W1876041327 hasConcept C129393996 @default.
- W1876041327 hasConcept C134306372 @default.
- W1876041327 hasConcept C144237770 @default.
- W1876041327 hasConcept C177148314 @default.
- W1876041327 hasConcept C180645754 @default.
- W1876041327 hasConcept C22171661 @default.
- W1876041327 hasConcept C2778755073 @default.
- W1876041327 hasConcept C33923547 @default.
- W1876041327 hasConcept C41008148 @default.
- W1876041327 hasConcept C48044578 @default.
- W1876041327 hasConcept C50817715 @default.
- W1876041327 hasConcept C62520636 @default.
- W1876041327 hasConcept C73602740 @default.
- W1876041327 hasConcept C77088390 @default.
- W1876041327 hasConcept C80444323 @default.
- W1876041327 hasConceptScore W1876041327C117160843 @default.
- W1876041327 hasConceptScore W1876041327C118615104 @default.
- W1876041327 hasConceptScore W1876041327C119857082 @default.
- W1876041327 hasConceptScore W1876041327C121332964 @default.
- W1876041327 hasConceptScore W1876041327C126255220 @default.
- W1876041327 hasConceptScore W1876041327C129393996 @default.
- W1876041327 hasConceptScore W1876041327C134306372 @default.
- W1876041327 hasConceptScore W1876041327C144237770 @default.
- W1876041327 hasConceptScore W1876041327C177148314 @default.
- W1876041327 hasConceptScore W1876041327C180645754 @default.
- W1876041327 hasConceptScore W1876041327C22171661 @default.
- W1876041327 hasConceptScore W1876041327C2778755073 @default.
- W1876041327 hasConceptScore W1876041327C33923547 @default.
- W1876041327 hasConceptScore W1876041327C41008148 @default.
- W1876041327 hasConceptScore W1876041327C48044578 @default.
- W1876041327 hasConceptScore W1876041327C50817715 @default.
- W1876041327 hasConceptScore W1876041327C62520636 @default.
- W1876041327 hasConceptScore W1876041327C73602740 @default.
- W1876041327 hasConceptScore W1876041327C77088390 @default.
- W1876041327 hasConceptScore W1876041327C80444323 @default.
- W1876041327 hasLocation W18760413271 @default.
- W1876041327 hasOpenAccess W1876041327 @default.
- W1876041327 hasPrimaryLocation W18760413271 @default.
- W1876041327 hasRelatedWork W1826788 @default.
- W1876041327 hasRelatedWork W1876041327 @default.