Shipra Agrawal

Citat de

	Toate	Din 2019
Referințe bibliografice	6903	4976
h-index	29	23
i10-index	40	31

960

480

240

720

200620072008200920102011201220132014201520162017201820192020202120222023202432 24 39 52 62 68 65 96 145 184 261 335 443 609 801 910 948 934 772

Acces public

Afișați-le pe toate

7 articole

1 articol

disponibile

indisponibile

Pe baza cerințelor privind finanțarea

Coautori

Yinyu YeK.T. Li Professor of Engineering, Stanford UniversityAdresă de e-mail confirmată pe stanford.edu
nikhil r. devanurAmazonAdresă de e-mail confirmată pe nikhildevanur.com
Jayant HaritsaIndian Institute of ScienceAdresă de e-mail confirmată pe iisc.ac.in
Zizhuo WangThe Chinese University of Hong Kong, Shenzhen / Cardinal OperationsAdresă de e-mail confirmată pe cuhk.edu.cn
Rajeev RastogiAmazonAdresă de e-mail confirmată pe amazon.com
Amin SaberiProfessor, Stanford UniversityAdresă de e-mail confirmată pe stanford.edu
Vijay KrishnanIIT Bombay, Stanford University, https://turing.comAdresă de e-mail confirmată pe cs.stanford.edu
Yichuan DingDesautels Faculty of Management, McGill UniversityAdresă de e-mail confirmată pe mcgill.ca
Lihong Li (李力鸿)AmazonAdresă de e-mail confirmată pe amazon.com
Tomáš KocákUniversity of PotsdamAdresă de e-mail confirmată pe uni-potsdam.de
Michal ValkoLlama @ Meta Paris & Inria & MVA - Ex: Gemini and BYOL @ Google DeepMindAdresă de e-mail confirmată pe meta.com
Rémi MunosGoogle DeepMindAdresă de e-mail confirmată pe inria.fr
Erick DelageProfessor, Department of Decision Sciences, HEC MontréalAdresă de e-mail confirmată pe hec.ca
Supratim DebTechnical Lead @ MetaAdresă de e-mail confirmată pe fb.com
B. Aditya PrakashAssociate Professor, Georgia Institute of TechnologyAdresă de e-mail confirmată pe cs.cmu.edu
Nimrod MegiddoDistinguished Research Staff Member, IBM Almaden Research CenterAdresă de e-mail confirmată pe us.ibm.com

Urmăriți

Shipra Agrawal

Columbia university

Adresă de e-mail confirmată pe columbia.edu - Pagina de pornire

multi-armed bandits reinforcement learning online and stochastic optmization


Titlu Sortați după descrierea bibliografică Sortați după an Sortați după titlu	Citat de Citat de	Anul
Analysis of thompson sampling for the multi-armed bandit problem S Agrawal, N Goyal Conference on learning theory, 39.1-39.26, 2012	1573	2012
Thompson sampling for contextual bandits with linear payoffs S Agrawal, N Goyal International conference on machine learning, 127-135, 2013	1201	2013
Near-optimal regret bounds for thompson sampling S Agrawal, N Goyal Journal of the ACM (JACM) 64 (5), 1-24, 2017	676	2017
A dynamic near-optimal algorithm for online linear programming S Agrawal, Z Wang, Y Ye Operations Research 62 (4), 876-890, 2014	352	2014
Optimistic posterior sampling for reinforcement learning: worst-case regret bounds S Agrawal, R Jia Advances in Neural Information Processing Systems 30, 2017	243	2017
A framework for high-accuracy privacy-preserving mining S Agrawal, JR Haritsa 21st International Conference on Data Engineering (ICDE'05), 193-204, 2005	241	2005
Bandits with concave rewards and convex knapsacks S Agrawal, NR Devanur Proceedings of the fifteenth ACM conference on Economics and computation …, 2014	232	2014
A near-optimal exploration-exploitation approach for assortment selection S Agrawal, V Avadhanula, V Goyal, A Zeevi Proceedings of the 2016 ACM Conference on Economics and Computation, 599-600, 2016	229*	2016
Reinforcement learning for integer programming: Learning to cut Y Tang, S Agrawal, Y Faenza International conference on machine learning, 9367-9376, 2020	216	2020
Fast Algorithms for Online Stochastic Convex Programming S Agrawal, NR Devanur SODA 2015, 2015	199	2015
Price of correlations in stochastic optimization S Agrawal, Y Ding, A Saberi, Y Ye Operations Research 60 (1), 150-162, 2012	173*	2012
Linear contextual bandits with knapsacks S Agrawal, N Devanur Advances in neural information processing systems 29, 2016	167	2016
Bandits with delayed, aggregated anonymous feedback C Pike-Burke, S Agrawal, C Szepesvari, S Grunewalder International Conference on Machine Learning, 4105-4113, 2018	133	2018
Discretizing continuous action space for on-policy optimization Y Tang, S Agrawal Proceedings of the aaai conference on artificial intelligence 34 (04), 5981-5988, 2020	131	2020
Thompson sampling for the mnl-bandit S Agrawal, V Avadhanula, V Goyal, A Zeevi Conference on learning theory, 76-78, 2017	123	2017
On addressing efficiency concerns in privacy-preserving mining S Agrawal, V Krishnan, JR Haritsa Database Systems for Advanced Applications: 9th International Conference …, 2004	111	2004
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives S Agrawal, NR Devanur, L Li Conference on Learning Theory, 4-18, 2016	109	2016
Learning in structured mdps with convex cost functions: Improved regret bounds for inventory management S Agrawal, R Jia Proceedings of the 2019 ACM Conference on Economics and Computation, 743-744, 2019	78	2019
Efficient detection of distributed constraint violations S Agrawal, S Deb, KVM Naidu, R Rastogi 2007 IEEE 23rd International Conference on Data Engineering, 1320-1324, 2006	76	2006
A unified framework for dynamic prediction market design S Agrawal, E Delage, M Peters, Z Wang, Y Ye Operations research 59 (3), 550-568, 2011	68*	2011

Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.

Articole 1–20

Referințe bibliografice pe an

Citate duplicat

Citate fuzionate

Adăugați coautoriCoautori

Urmăriți

Citat de

Coautori