Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297757002> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4297757002 abstract "Optimal stopping is the problem of determining when to stop a stochastic system in order to maximize reward, which is of practical importance in domains such as finance, operations management and healthcare. Existing methods for high-dimensional optimal stopping that are popular in practice produce deterministic linear policies -- policies that deterministically stop based on the sign of a weighted sum of basis functions -- but are not guaranteed to find the optimal policy within this policy class given a fixed basis function architecture. In this paper, we propose a new methodology for optimal stopping based on randomized linear policies, which choose to stop with a probability that is determined by a weighted sum of basis functions. We motivate these policies by establishing that under mild conditions, given a fixed basis function architecture, optimizing over randomized linear policies is equivalent to optimizing over deterministic linear policies. We formulate the problem of learning randomized linear policies from data as a smooth non-convex sample average approximation (SAA) problem. We theoretically prove the almost sure convergence of our randomized policy SAA problem and establish bounds on the out-of-sample performance of randomized policies obtained from our SAA problem based on Rademacher complexity. We also show that the SAA problem is in general NP-Hard, and consequently develop a practical heuristic for solving our randomized policy problem. Through numerical experiments on a benchmark family of option pricing problem instances, we show that our approach can substantially outperform state-of-the-art methods." @default.
- W4297757002 created "2022-10-01" @default.
- W4297757002 creator A5042068161 @default.
- W4297757002 creator A5074115249 @default.
- W4297757002 date "2022-03-25" @default.
- W4297757002 modified "2023-09-30" @default.
- W4297757002 title "Randomized Policy Optimization for Optimal Stopping" @default.
- W4297757002 doi "https://doi.org/10.48550/arxiv.2203.13446" @default.
- W4297757002 hasPublicationYear "2022" @default.
- W4297757002 type Work @default.
- W4297757002 citedByCount "0" @default.
- W4297757002 crossrefType "posted-content" @default.
- W4297757002 hasAuthorship W4297757002A5042068161 @default.
- W4297757002 hasAuthorship W4297757002A5074115249 @default.
- W4297757002 hasBestOaLocation W42977570021 @default.
- W4297757002 hasConcept C105795698 @default.
- W4297757002 hasConcept C11413529 @default.
- W4297757002 hasConcept C12426560 @default.
- W4297757002 hasConcept C126255220 @default.
- W4297757002 hasConcept C128669082 @default.
- W4297757002 hasConcept C13280743 @default.
- W4297757002 hasConcept C14036430 @default.
- W4297757002 hasConcept C162324750 @default.
- W4297757002 hasConcept C173801870 @default.
- W4297757002 hasConcept C185592680 @default.
- W4297757002 hasConcept C185798385 @default.
- W4297757002 hasConcept C198531522 @default.
- W4297757002 hasConcept C205649164 @default.
- W4297757002 hasConcept C2524010 @default.
- W4297757002 hasConcept C2777303404 @default.
- W4297757002 hasConcept C33923547 @default.
- W4297757002 hasConcept C41008148 @default.
- W4297757002 hasConcept C43617362 @default.
- W4297757002 hasConcept C50522688 @default.
- W4297757002 hasConcept C78458016 @default.
- W4297757002 hasConcept C86803240 @default.
- W4297757002 hasConcept C99414536 @default.
- W4297757002 hasConcept C99888217 @default.
- W4297757002 hasConceptScore W4297757002C105795698 @default.
- W4297757002 hasConceptScore W4297757002C11413529 @default.
- W4297757002 hasConceptScore W4297757002C12426560 @default.
- W4297757002 hasConceptScore W4297757002C126255220 @default.
- W4297757002 hasConceptScore W4297757002C128669082 @default.
- W4297757002 hasConceptScore W4297757002C13280743 @default.
- W4297757002 hasConceptScore W4297757002C14036430 @default.
- W4297757002 hasConceptScore W4297757002C162324750 @default.
- W4297757002 hasConceptScore W4297757002C173801870 @default.
- W4297757002 hasConceptScore W4297757002C185592680 @default.
- W4297757002 hasConceptScore W4297757002C185798385 @default.
- W4297757002 hasConceptScore W4297757002C198531522 @default.
- W4297757002 hasConceptScore W4297757002C205649164 @default.
- W4297757002 hasConceptScore W4297757002C2524010 @default.
- W4297757002 hasConceptScore W4297757002C2777303404 @default.
- W4297757002 hasConceptScore W4297757002C33923547 @default.
- W4297757002 hasConceptScore W4297757002C41008148 @default.
- W4297757002 hasConceptScore W4297757002C43617362 @default.
- W4297757002 hasConceptScore W4297757002C50522688 @default.
- W4297757002 hasConceptScore W4297757002C78458016 @default.
- W4297757002 hasConceptScore W4297757002C86803240 @default.
- W4297757002 hasConceptScore W4297757002C99414536 @default.
- W4297757002 hasConceptScore W4297757002C99888217 @default.
- W4297757002 hasLocation W42977570021 @default.
- W4297757002 hasOpenAccess W4297757002 @default.
- W4297757002 hasPrimaryLocation W42977570021 @default.
- W4297757002 hasRelatedWork W1985012061 @default.
- W4297757002 hasRelatedWork W2003480636 @default.
- W4297757002 hasRelatedWork W2106556139 @default.
- W4297757002 hasRelatedWork W2159757177 @default.
- W4297757002 hasRelatedWork W2207002589 @default.
- W4297757002 hasRelatedWork W2236369119 @default.
- W4297757002 hasRelatedWork W2289289167 @default.
- W4297757002 hasRelatedWork W2611363004 @default.
- W4297757002 hasRelatedWork W3111453649 @default.
- W4297757002 hasRelatedWork W802275573 @default.
- W4297757002 isParatext "false" @default.
- W4297757002 isRetracted "false" @default.
- W4297757002 workType "article" @default.