FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3006608344> ?p ?o ?g. }

• W3006608344 abstract "In this paper, we study the well-known stochastic linear bandit problem where a decision-maker sequentially chooses among a set of given actions in $mathbb{R}^d$, observes their noisy linear reward, and aims to maximize her cumulative expected reward over a horizon of length $T$. We first introduce a general family of algorithms for the problem and prove that they achieve the best-known performance (aka, are rate optimal). Our second contribution is to show that several well-known algorithms for the problem such as optimism in the face of uncertainty linear bandit (OFUL), Thompson sampling (TS), and OLS Bandit (a variant $epsilon$-greedy) are special cases of our family of algorithms. Therefore, we obtain a unified proof of rate optimality for all of these algorithms, for both Bayesian and frequentist settings. Our new unified technique also yields a number of new results such as obtaining poly-logarithmic (in $T$) regret bounds for OFUL and TS, under a generalized gap assumption and a margin condition as in Goldenshluger and Zeevi (2013). A key component of our analysis technique is the introduction of a new notion of uncertainty complexity that directly captures the complexity of uncertainty in the action sets that we show is connected to regret analysis of any policy. Our third and most important contribution, from both theoretical and practical points of view, is the introduction of a new rate-optimal algorithm called Sieved-Greedy (SG) by combining insights from uncertainty complexity and a new (and general) notion of optimism in expectation. Specifically, SG works by filtering out the actions with relatively low uncertainty and then chooses one among the remaining actions greedily. Our empirical simulations show that SG significantly outperforms existing benchmarks by combining the best attributes of both greedy and OFUL algorithms." @default.
• W3006608344 created "2020-02-24" @default.
• W3006608344 creator A5048079293 @default.
• W3006608344 creator A5091599934 @default.
• W3006608344 date "2020-02-12" @default.
• W3006608344 modified "2023-09-27" @default.
• W3006608344 title "A General Framework to Analyze Stochastic Linear Bandit" @default.
• W3006608344 cites W1560153690 @default.
• W3006608344 cites W1595135966 @default.
• W3006608344 cites W2039522160 @default.
• W3006608344 cites W2061753713 @default.
• W3006608344 cites W2069129115 @default.
• W3006608344 cites W2119738618 @default.
• W3006608344 cites W2130527179 @default.
• W3006608344 cites W2149721706 @default.
• W3006608344 cites W2158125716 @default.
• W3006608344 cites W2166253248 @default.
• W3006608344 cites W2491144192 @default.
• W3006608344 cites W2744538883 @default.
• W3006608344 cites W2773557179 @default.
• W3006608344 cites W2787284768 @default.
• W3006608344 cites W2805217655 @default.
• W3006608344 cites W2805596211 @default.
• W3006608344 cites W2951665052 @default.
• W3006608344 cites W2953138456 @default.
• W3006608344 cites W2962901934 @default.
• W3006608344 cites W2963007936 @default.
• W3006608344 cites W2963147981 @default.
• W3006608344 cites W2964035670 @default.
• W3006608344 cites W2980763555 @default.
• W3006608344 cites W3044872185 @default.
• W3006608344 cites W3094238780 @default.
• W3006608344 cites W3124121179 @default.
• W3006608344 cites W50486269 @default.
• W3006608344 hasPublicationYear "2020" @default.
• W3006608344 type Work @default.
• W3006608344 sameAs 3006608344 @default.
• W3006608344 citedByCount "1" @default.
• W3006608344 countsByYear W30066083442020 @default.
• W3006608344 crossrefType "posted-content" @default.
• W3006608344 hasAuthorship W3006608344A5048079293 @default.
• W3006608344 hasAuthorship W3006608344A5091599934 @default.
• W3006608344 hasConcept C105795698 @default.
• W3006608344 hasConcept C107673813 @default.
• W3006608344 hasConcept C126255220 @default.
• W3006608344 hasConcept C134306372 @default.
• W3006608344 hasConcept C154945302 @default.
• W3006608344 hasConcept C160234255 @default.
• W3006608344 hasConcept C162376815 @default.
• W3006608344 hasConcept C33923547 @default.
• W3006608344 hasConcept C39927690 @default.
• W3006608344 hasConcept C41008148 @default.
• W3006608344 hasConcept C50817715 @default.
• W3006608344 hasConcept C73602740 @default.
• W3006608344 hasConceptScore W3006608344C105795698 @default.
• W3006608344 hasConceptScore W3006608344C107673813 @default.
• W3006608344 hasConceptScore W3006608344C126255220 @default.
• W3006608344 hasConceptScore W3006608344C134306372 @default.
• W3006608344 hasConceptScore W3006608344C154945302 @default.
• W3006608344 hasConceptScore W3006608344C160234255 @default.
• W3006608344 hasConceptScore W3006608344C162376815 @default.
• W3006608344 hasConceptScore W3006608344C33923547 @default.
• W3006608344 hasConceptScore W3006608344C39927690 @default.
• W3006608344 hasConceptScore W3006608344C41008148 @default.
• W3006608344 hasConceptScore W3006608344C50817715 @default.
• W3006608344 hasConceptScore W3006608344C73602740 @default.
• W3006608344 hasLocation W30066083441 @default.
• W3006608344 hasOpenAccess W3006608344 @default.
• W3006608344 hasPrimaryLocation W30066083441 @default.
• W3006608344 hasRelatedWork W148375489 @default.
• W3006608344 hasRelatedWork W1501823362 @default.
• W3006608344 hasRelatedWork W1505937442 @default.
• W3006608344 hasRelatedWork W1510812122 @default.
• W3006608344 hasRelatedWork W1536615069 @default.
• W3006608344 hasRelatedWork W1538601471 @default.
• W3006608344 hasRelatedWork W1553290137 @default.
• W3006608344 hasRelatedWork W1556834409 @default.
• W3006608344 hasRelatedWork W157259654 @default.
• W3006608344 hasRelatedWork W159910205 @default.
• W3006608344 hasRelatedWork W166250193 @default.
• W3006608344 hasRelatedWork W168489101 @default.
• W3006608344 hasRelatedWork W172143579 @default.
• W3006608344 hasRelatedWork W1911551976 @default.
• W3006608344 hasRelatedWork W2009551863 @default.
• W3006608344 hasRelatedWork W2039522160 @default.
• W3006608344 hasRelatedWork W2149721706 @default.
• W3006608344 hasRelatedWork W38462774 @default.
• W3006608344 hasRelatedWork W50486269 @default.
• W3006608344 hasRelatedWork W77456527 @default.
• W3006608344 isParatext "false" @default.
• W3006608344 isRetracted "false" @default.
• W3006608344 magId "3006608344" @default.
• W3006608344 workType "article" @default.