Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128715451> ?p ?o ?g. }
- W3128715451 endingPage "6115" @default.
- W3128715451 startingPage "6089" @default.
- W3128715451 abstract "We consider a periodic-review single-product inventory system with fixed cost under censored demand. Under full demand distributional information, it is well known that the celebrated (s, S) policy is optimal. In this paper, we assume the firm does not know the demand distribution a priori and makes adaptive inventory ordering decisions in each period based only on the past sales (a.k.a. censored demand). Our performance measure is regret, which is the cost difference between a feasible learning algorithm and the clairvoyant (full-information) benchmark. Compared with prior literature, the key difficulty of this problem lies in the loss of joint convexity of the objective function as a result of the presence of fixed cost. We develop the first learning algorithm, termed the [Formula: see text] policy, that combines the power of stochastic gradient descent, bandit controls, and simulation-based methods in a seamless and nontrivial fashion. We prove that the cumulative regret is [Formula: see text], which is provably tight up to a logarithmic factor. We also develop several technical results that are of independent interest. We believe that the developed framework could be widely applied to learning other important stochastic systems with partial convexity in the objectives. This paper was accepted by Chung Piaw Teo, optimization." @default.
- W3128715451 created "2021-02-15" @default.
- W3128715451 creator A5023311569 @default.
- W3128715451 creator A5063297865 @default.
- W3128715451 creator A5068230310 @default.
- W3128715451 date "2021-10-01" @default.
- W3128715451 modified "2023-10-10" @default.
- W3128715451 title "Marrying Stochastic Gradient Descent with Bandits: Learning Algorithms for Inventory Systems with Fixed Costs" @default.
- W3128715451 cites W1622454718 @default.
- W3128715451 cites W1828651507 @default.
- W3128715451 cites W1967158814 @default.
- W3128715451 cites W1983916623 @default.
- W3128715451 cites W1990482617 @default.
- W3128715451 cites W1992603718 @default.
- W3128715451 cites W1997000352 @default.
- W3128715451 cites W2001608256 @default.
- W3128715451 cites W2009395351 @default.
- W3128715451 cites W2017036124 @default.
- W3128715451 cites W2021380229 @default.
- W3128715451 cites W2021708247 @default.
- W3128715451 cites W2023498995 @default.
- W3128715451 cites W2024817131 @default.
- W3128715451 cites W2029806612 @default.
- W3128715451 cites W2032091434 @default.
- W3128715451 cites W2035380861 @default.
- W3128715451 cites W2043520942 @default.
- W3128715451 cites W2051206585 @default.
- W3128715451 cites W2059470728 @default.
- W3128715451 cites W2060472015 @default.
- W3128715451 cites W2080658196 @default.
- W3128715451 cites W2090343757 @default.
- W3128715451 cites W2101913016 @default.
- W3128715451 cites W2102953461 @default.
- W3128715451 cites W2106985921 @default.
- W3128715451 cites W2111669004 @default.
- W3128715451 cites W2112051922 @default.
- W3128715451 cites W2114908964 @default.
- W3128715451 cites W2115519224 @default.
- W3128715451 cites W2117996383 @default.
- W3128715451 cites W2120377617 @default.
- W3128715451 cites W2122897173 @default.
- W3128715451 cites W2122975995 @default.
- W3128715451 cites W2129430585 @default.
- W3128715451 cites W2130184319 @default.
- W3128715451 cites W2130873555 @default.
- W3128715451 cites W2140742596 @default.
- W3128715451 cites W2156028130 @default.
- W3128715451 cites W2159535190 @default.
- W3128715451 cites W2160172818 @default.
- W3128715451 cites W2162094362 @default.
- W3128715451 cites W2164063315 @default.
- W3128715451 cites W2166199188 @default.
- W3128715451 cites W2171027013 @default.
- W3128715451 cites W2191508049 @default.
- W3128715451 cites W2208994903 @default.
- W3128715451 cites W2314247578 @default.
- W3128715451 cites W2616265545 @default.
- W3128715451 cites W2884330776 @default.
- W3128715451 cites W2892159387 @default.
- W3128715451 cites W2953305686 @default.
- W3128715451 cites W2956003076 @default.
- W3128715451 cites W3122908781 @default.
- W3128715451 cites W3125367953 @default.
- W3128715451 cites W3125747142 @default.
- W3128715451 cites W4205841652 @default.
- W3128715451 cites W4211030719 @default.
- W3128715451 cites W4214827656 @default.
- W3128715451 cites W4292022450 @default.
- W3128715451 doi "https://doi.org/10.1287/mnsc.2020.3799" @default.
- W3128715451 hasPublicationYear "2021" @default.
- W3128715451 type Work @default.
- W3128715451 sameAs 3128715451 @default.
- W3128715451 citedByCount "30" @default.
- W3128715451 countsByYear W31287154512012 @default.
- W3128715451 countsByYear W31287154512019 @default.
- W3128715451 countsByYear W31287154512020 @default.
- W3128715451 countsByYear W31287154512021 @default.
- W3128715451 countsByYear W31287154512022 @default.
- W3128715451 countsByYear W31287154512023 @default.
- W3128715451 crossrefType "journal-article" @default.
- W3128715451 hasAuthorship W3128715451A5023311569 @default.
- W3128715451 hasAuthorship W3128715451A5063297865 @default.
- W3128715451 hasAuthorship W3128715451A5068230310 @default.
- W3128715451 hasConcept C106159729 @default.
- W3128715451 hasConcept C111472728 @default.
- W3128715451 hasConcept C119857082 @default.
- W3128715451 hasConcept C126255220 @default.
- W3128715451 hasConcept C13280743 @default.
- W3128715451 hasConcept C134306372 @default.
- W3128715451 hasConcept C138885662 @default.
- W3128715451 hasConcept C162324750 @default.
- W3128715451 hasConcept C185798385 @default.
- W3128715451 hasConcept C205649164 @default.
- W3128715451 hasConcept C26517878 @default.
- W3128715451 hasConcept C33923547 @default.
- W3128715451 hasConcept C38652104 @default.
- W3128715451 hasConcept C39927690 @default.
- W3128715451 hasConcept C41008148 @default.