Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094031561> ?p ?o ?g. }
- W3094031561 abstract "Tractable contextual bandit algorithms often rely on the realizability assumption - i.e., that the true expected reward model belongs to a known class, such as linear functions. In this work, we present a tractable bandit algorithm that is not sensitive to the realizability assumption and computationally reduces to solving a constrained regression problem in every epoch. When realizability does not hold, our algorithm ensures the same guarantees on regret achieved by realizability-based algorithms under realizability, up to an additive term that accounts for the misspecification error. This extra term is proportional to T times a function of the mean squared error between the best model in the class and the true model, where T is the total number of time-steps. Our work sheds light on the bias-variance trade-off for tractable contextual bandits. This trade-off is not captured by algorithms that assume realizability, since under this assumption there exists an estimator in the class that attains zero bias." @default.
- W3094031561 created "2020-10-29" @default.
- W3094031561 creator A5001211242 @default.
- W3094031561 creator A5017697122 @default.
- W3094031561 creator A5083438983 @default.
- W3094031561 date "2020-10-25" @default.
- W3094031561 modified "2023-09-27" @default.
- W3094031561 title "Tractable contextual bandits beyond realizability" @default.
- W3094031561 cites W1595135966 @default.
- W3094031561 cites W1687714866 @default.
- W3094031561 cites W2003238113 @default.
- W3094031561 cites W2098258765 @default.
- W3094031561 cites W2103715332 @default.
- W3094031561 cites W2112420033 @default.
- W3094031561 cites W2119738618 @default.
- W3094031561 cites W2166253248 @default.
- W3094031561 cites W2588616261 @default.
- W3094031561 cites W2614208603 @default.
- W3094031561 cites W2734936460 @default.
- W3094031561 cites W2790576010 @default.
- W3094031561 cites W2947761153 @default.
- W3094031561 cites W2951270685 @default.
- W3094031561 cites W2963007936 @default.
- W3094031561 cites W2963964957 @default.
- W3094031561 cites W2964163363 @default.
- W3094031561 cites W2971064883 @default.
- W3094031561 cites W2982152536 @default.
- W3094031561 cites W3009712390 @default.
- W3094031561 cites W3013725403 @default.
- W3094031561 cites W3029968658 @default.
- W3094031561 cites W3034274776 @default.
- W3094031561 cites W3034360859 @default.
- W3094031561 cites W3034897261 @default.
- W3094031561 cites W3099649246 @default.
- W3094031561 cites W3100895096 @default.
- W3094031561 hasPublicationYear "2020" @default.
- W3094031561 type Work @default.
- W3094031561 sameAs 3094031561 @default.
- W3094031561 citedByCount "1" @default.
- W3094031561 countsByYear W30940315612021 @default.
- W3094031561 crossrefType "posted-content" @default.
- W3094031561 hasAuthorship W3094031561A5001211242 @default.
- W3094031561 hasAuthorship W3094031561A5017697122 @default.
- W3094031561 hasAuthorship W3094031561A5083438983 @default.
- W3094031561 hasConcept C105795698 @default.
- W3094031561 hasConcept C11413529 @default.
- W3094031561 hasConcept C121332964 @default.
- W3094031561 hasConcept C121955636 @default.
- W3094031561 hasConcept C126255220 @default.
- W3094031561 hasConcept C144133560 @default.
- W3094031561 hasConcept C154945302 @default.
- W3094031561 hasConcept C185429906 @default.
- W3094031561 hasConcept C196083921 @default.
- W3094031561 hasConcept C2776378722 @default.
- W3094031561 hasConcept C2777212361 @default.
- W3094031561 hasConcept C33923547 @default.
- W3094031561 hasConcept C41008148 @default.
- W3094031561 hasConcept C50817715 @default.
- W3094031561 hasConcept C61797465 @default.
- W3094031561 hasConcept C62520636 @default.
- W3094031561 hasConceptScore W3094031561C105795698 @default.
- W3094031561 hasConceptScore W3094031561C11413529 @default.
- W3094031561 hasConceptScore W3094031561C121332964 @default.
- W3094031561 hasConceptScore W3094031561C121955636 @default.
- W3094031561 hasConceptScore W3094031561C126255220 @default.
- W3094031561 hasConceptScore W3094031561C144133560 @default.
- W3094031561 hasConceptScore W3094031561C154945302 @default.
- W3094031561 hasConceptScore W3094031561C185429906 @default.
- W3094031561 hasConceptScore W3094031561C196083921 @default.
- W3094031561 hasConceptScore W3094031561C2776378722 @default.
- W3094031561 hasConceptScore W3094031561C2777212361 @default.
- W3094031561 hasConceptScore W3094031561C33923547 @default.
- W3094031561 hasConceptScore W3094031561C41008148 @default.
- W3094031561 hasConceptScore W3094031561C50817715 @default.
- W3094031561 hasConceptScore W3094031561C61797465 @default.
- W3094031561 hasConceptScore W3094031561C62520636 @default.
- W3094031561 hasLocation W30940315611 @default.
- W3094031561 hasOpenAccess W3094031561 @default.
- W3094031561 hasPrimaryLocation W30940315611 @default.
- W3094031561 hasRelatedWork W2491144192 @default.
- W3094031561 hasRelatedWork W2592998600 @default.
- W3094031561 hasRelatedWork W2604278489 @default.
- W3094031561 hasRelatedWork W2950640409 @default.
- W3094031561 hasRelatedWork W2963030561 @default.
- W3094031561 hasRelatedWork W3012582392 @default.
- W3094031561 hasRelatedWork W3013725403 @default.
- W3094031561 hasRelatedWork W3035613237 @default.
- W3094031561 hasRelatedWork W3091852560 @default.
- W3094031561 hasRelatedWork W3099649246 @default.
- W3094031561 hasRelatedWork W3099809348 @default.
- W3094031561 hasRelatedWork W3134826391 @default.
- W3094031561 hasRelatedWork W3157650980 @default.
- W3094031561 hasRelatedWork W3158121932 @default.
- W3094031561 hasRelatedWork W3158925485 @default.
- W3094031561 hasRelatedWork W3167063605 @default.
- W3094031561 hasRelatedWork W3173089934 @default.
- W3094031561 hasRelatedWork W3179425315 @default.
- W3094031561 hasRelatedWork W3212747081 @default.
- W3094031561 hasRelatedWork W3213370222 @default.
- W3094031561 isParatext "false" @default.