Matches in SemOpenAlex for { <https://semopenalex.org/work/W2810113936> ?p ?o ?g. }
- W2810113936 abstract "We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, potentially data-dependent, regularization technique for CRM. Experimental results indicate that this technique outperforms standard $L_2$ regularization, and that it is competitive with variance regularization while being both simpler to implement and more computationally efficient." @default.
- W2810113936 created "2018-07-10" @default.
- W2810113936 creator A5047338645 @default.
- W2810113936 creator A5054561921 @default.
- W2810113936 date "2018-06-29" @default.
- W2810113936 modified "2023-09-27" @default.
- W2810113936 title "Bayesian Counterfactual Risk Minimization" @default.
- W2810113936 cites W1607832978 @default.
- W2810113936 cites W1771410628 @default.
- W2810113936 cites W1835900096 @default.
- W2810113936 cites W2001947543 @default.
- W2810113936 cites W2020160576 @default.
- W2810113936 cites W2029029543 @default.
- W2810113936 cites W2086206379 @default.
- W2810113936 cites W2107074784 @default.
- W2810113936 cites W2108598243 @default.
- W2810113936 cites W2108738385 @default.
- W2810113936 cites W2108810117 @default.
- W2810113936 cites W2113065326 @default.
- W2810113936 cites W2116942894 @default.
- W2810113936 cites W2122124659 @default.
- W2810113936 cites W2130464645 @default.
- W2810113936 cites W2146502635 @default.
- W2810113936 cites W2146807381 @default.
- W2810113936 cites W2149991487 @default.
- W2810113936 cites W2150291618 @default.
- W2810113936 cites W2155027007 @default.
- W2810113936 cites W2168022998 @default.
- W2810113936 cites W2188353343 @default.
- W2810113936 cites W2194775991 @default.
- W2810113936 cites W2601021979 @default.
- W2810113936 cites W2750384547 @default.
- W2810113936 cites W2785875001 @default.
- W2810113936 cites W2962724006 @default.
- W2810113936 cites W2963669158 @default.
- W2810113936 cites W2963862827 @default.
- W2810113936 cites W2964297722 @default.
- W2810113936 cites W3118608800 @default.
- W2810113936 cites W2093257937 @default.
- W2810113936 hasPublicationYear "2018" @default.
- W2810113936 type Work @default.
- W2810113936 sameAs 2810113936 @default.
- W2810113936 citedByCount "0" @default.
- W2810113936 crossrefType "posted-content" @default.
- W2810113936 hasAuthorship W2810113936A5047338645 @default.
- W2810113936 hasAuthorship W2810113936A5054561921 @default.
- W2810113936 hasConcept C105795698 @default.
- W2810113936 hasConcept C107673813 @default.
- W2810113936 hasConcept C108650721 @default.
- W2810113936 hasConcept C119857082 @default.
- W2810113936 hasConcept C126255220 @default.
- W2810113936 hasConcept C134306372 @default.
- W2810113936 hasConcept C147764199 @default.
- W2810113936 hasConcept C149782125 @default.
- W2810113936 hasConcept C154945302 @default.
- W2810113936 hasConcept C15744967 @default.
- W2810113936 hasConcept C177148314 @default.
- W2810113936 hasConcept C17923572 @default.
- W2810113936 hasConcept C185429906 @default.
- W2810113936 hasConcept C207467116 @default.
- W2810113936 hasConcept C2524010 @default.
- W2810113936 hasConcept C2776135515 @default.
- W2810113936 hasConcept C33923547 @default.
- W2810113936 hasConcept C41008148 @default.
- W2810113936 hasConcept C77805123 @default.
- W2810113936 hasConceptScore W2810113936C105795698 @default.
- W2810113936 hasConceptScore W2810113936C107673813 @default.
- W2810113936 hasConceptScore W2810113936C108650721 @default.
- W2810113936 hasConceptScore W2810113936C119857082 @default.
- W2810113936 hasConceptScore W2810113936C126255220 @default.
- W2810113936 hasConceptScore W2810113936C134306372 @default.
- W2810113936 hasConceptScore W2810113936C147764199 @default.
- W2810113936 hasConceptScore W2810113936C149782125 @default.
- W2810113936 hasConceptScore W2810113936C154945302 @default.
- W2810113936 hasConceptScore W2810113936C15744967 @default.
- W2810113936 hasConceptScore W2810113936C177148314 @default.
- W2810113936 hasConceptScore W2810113936C17923572 @default.
- W2810113936 hasConceptScore W2810113936C185429906 @default.
- W2810113936 hasConceptScore W2810113936C207467116 @default.
- W2810113936 hasConceptScore W2810113936C2524010 @default.
- W2810113936 hasConceptScore W2810113936C2776135515 @default.
- W2810113936 hasConceptScore W2810113936C33923547 @default.
- W2810113936 hasConceptScore W2810113936C41008148 @default.
- W2810113936 hasConceptScore W2810113936C77805123 @default.
- W2810113936 hasLocation W28101139361 @default.
- W2810113936 hasOpenAccess W2810113936 @default.
- W2810113936 hasPrimaryLocation W28101139361 @default.
- W2810113936 hasRelatedWork W1578367602 @default.
- W2810113936 hasRelatedWork W1788984484 @default.
- W2810113936 hasRelatedWork W1965520710 @default.
- W2810113936 hasRelatedWork W2068451409 @default.
- W2810113936 hasRelatedWork W2087757986 @default.
- W2810113936 hasRelatedWork W2090946435 @default.
- W2810113936 hasRelatedWork W2129827384 @default.
- W2810113936 hasRelatedWork W2156140776 @default.
- W2810113936 hasRelatedWork W232754960 @default.
- W2810113936 hasRelatedWork W2903743315 @default.
- W2810113936 hasRelatedWork W2947972834 @default.
- W2810113936 hasRelatedWork W2949374347 @default.
- W2810113936 hasRelatedWork W2952400139 @default.