Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920202034> ?p ?o ?g. }
- W2920202034 abstract "We introduce data-driven decision-making algorithms that achieve state-of-the-art emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and traffic network routing in changing environments. We show how the difficulty posed by the (unknown emph{a priori} and possibly adversarial) non-stationarity can be overcome by an unconventional marriage between stochastic and adversarial bandit learning algorithms. Our main contribution is a general algorithmic recipe for a wide variety of non-stationary bandit problems. Specifically, we design and analyze the sliding window-upper confidence bound algorithm that achieves the optimal dynamic regret bound for each of the settings when we know the respective underlying emph{variation budget}, which quantifies the total amount of temporal variation of the latent environments. Boosted by the novel bandit-over-bandit framework that adapts to the latent changes, we can further enjoy the (nearly) optimal dynamic regret bounds in a (surprisingly) parameter-free manner. In addition to the classical exploration-exploitation trade-off, our algorithms leverage the power of the forgetting principle in the learning processes, which is vital in changing environments. Our extensive numerical experiments on both synthetic and real world online auto-loan datasets show that our proposed algorithms achieve superior empirical performance compared to existing algorithms." @default.
- W2920202034 created "2019-03-11" @default.
- W2920202034 creator A5010450673 @default.
- W2920202034 creator A5038115830 @default.
- W2920202034 creator A5078130712 @default.
- W2920202034 date "2019-03-04" @default.
- W2920202034 modified "2023-09-26" @default.
- W2920202034 title "Hedging the Drift: Learning to Optimize under Non-Stationarity" @default.
- W2920202034 cites W1487320471 @default.
- W2920202034 cites W1510812122 @default.
- W2920202034 cites W1570963478 @default.
- W2920202034 cites W157259654 @default.
- W2920202034 cites W2034284198 @default.
- W2920202034 cites W2049934117 @default.
- W2920202034 cites W2061753713 @default.
- W2920202034 cites W2077902449 @default.
- W2920202034 cites W2093562354 @default.
- W2920202034 cites W2108114251 @default.
- W2920202034 cites W2112420033 @default.
- W2920202034 cites W2119738618 @default.
- W2920202034 cites W2149721706 @default.
- W2920202034 cites W2160163723 @default.
- W2920202034 cites W2161509455 @default.
- W2920202034 cites W2166253248 @default.
- W2920202034 cites W2168405694 @default.
- W2920202034 cites W2186453173 @default.
- W2920202034 cites W2553494220 @default.
- W2920202034 cites W2555558374 @default.
- W2920202034 cites W2592998600 @default.
- W2920202034 cites W2619385028 @default.
- W2920202034 cites W2742123006 @default.
- W2920202034 cites W2752885492 @default.
- W2920202034 cites W2911079225 @default.
- W2920202034 cites W2917261185 @default.
- W2920202034 cites W2948345763 @default.
- W2920202034 cites W2949107315 @default.
- W2920202034 cites W2951586296 @default.
- W2920202034 cites W2951665052 @default.
- W2920202034 cites W2958951938 @default.
- W2920202034 cites W2962739885 @default.
- W2920202034 cites W2962821829 @default.
- W2920202034 cites W2962847271 @default.
- W2920202034 cites W2963201118 @default.
- W2920202034 cites W2963382851 @default.
- W2920202034 cites W2964007796 @default.
- W2920202034 cites W2964132277 @default.
- W2920202034 cites W2964163363 @default.
- W2920202034 cites W2966078592 @default.
- W2920202034 cites W2966236865 @default.
- W2920202034 cites W2971064883 @default.
- W2920202034 cites W3002773505 @default.
- W2920202034 cites W3024171650 @default.
- W2920202034 cites W3025093529 @default.
- W2920202034 cites W3085631657 @default.
- W2920202034 cites W3092949629 @default.
- W2920202034 cites W3122984207 @default.
- W2920202034 cites W3123661679 @default.
- W2920202034 cites W3125579698 @default.
- W2920202034 cites W3145128584 @default.
- W2920202034 cites W3211898143 @default.
- W2920202034 cites W50486269 @default.
- W2920202034 cites W2098339418 @default.
- W2920202034 doi "https://doi.org/10.48550/arxiv.1903.01461" @default.
- W2920202034 hasPublicationYear "2019" @default.
- W2920202034 type Work @default.
- W2920202034 sameAs 2920202034 @default.
- W2920202034 citedByCount "19" @default.
- W2920202034 countsByYear W29202020342019 @default.
- W2920202034 countsByYear W29202020342020 @default.
- W2920202034 countsByYear W29202020342021 @default.
- W2920202034 crossrefType "posted-content" @default.
- W2920202034 hasAuthorship W2920202034A5010450673 @default.
- W2920202034 hasAuthorship W2920202034A5038115830 @default.
- W2920202034 hasAuthorship W2920202034A5078130712 @default.
- W2920202034 hasBestOaLocation W29202020341 @default.
- W2920202034 hasConcept C111472728 @default.
- W2920202034 hasConcept C119857082 @default.
- W2920202034 hasConcept C121332964 @default.
- W2920202034 hasConcept C123197309 @default.
- W2920202034 hasConcept C126255220 @default.
- W2920202034 hasConcept C134306372 @default.
- W2920202034 hasConcept C136197465 @default.
- W2920202034 hasConcept C138885662 @default.
- W2920202034 hasConcept C144133560 @default.
- W2920202034 hasConcept C153083717 @default.
- W2920202034 hasConcept C154945302 @default.
- W2920202034 hasConcept C162853370 @default.
- W2920202034 hasConcept C2778334786 @default.
- W2920202034 hasConcept C2779391423 @default.
- W2920202034 hasConcept C33923547 @default.
- W2920202034 hasConcept C41008148 @default.
- W2920202034 hasConcept C41895202 @default.
- W2920202034 hasConcept C44870925 @default.
- W2920202034 hasConcept C50817715 @default.
- W2920202034 hasConcept C7149132 @default.
- W2920202034 hasConcept C75553542 @default.
- W2920202034 hasConcept C77553402 @default.
- W2920202034 hasConceptScore W2920202034C111472728 @default.
- W2920202034 hasConceptScore W2920202034C119857082 @default.
- W2920202034 hasConceptScore W2920202034C121332964 @default.