Abbas Mehrabian

Cited by

	All	Since 2019
Citations	1882	1590
h-index	18	14
i10-index	23	17

380

190

285

2011201220132014201520162017201820192020202120222023202415 18 18 27 39 42 50 65 127 212 248 312 324 364

Public access

View all

15 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Christopher LiawResearch Scientist, GoogleVerified email at google.com
Nicholas J. A. HarveyProfessor of Computer Science, University of British ColumbiaVerified email at cs.ubc.ca
Luc DevroyeMcGill UniversityVerified email at cs.mcgill.ca
Hassan AshtianiMcMaster UniversityVerified email at mcmaster.ca
Shai Ben-DavidUniverity of Waterloo, CanadaVerified email at uwaterloo.ca
Yaniv PlanUniversity of British ColumbiaVerified email at math.ubc.ca
Peter BartlettProfessor, EECS and Statistics, UC BerkeleyVerified email at cs.berkeley.edu
Noga AlonPrinceton University and Tel Aviv UniversityVerified email at tau.ac.il
Andrea CollevecchioMonash University, School of Mathematical SciencesVerified email at monash.edu
Vahab MirrokniGoogle Fellow, VP, Google ResearchVerified email at google.com
Amin KarbasiRobust Intelligence, Yale University (on leave)Verified email at yale.edu
Hossein EsfandiariSenior Research Scientist at GoogleVerified email at seas.harvard.edu
Emilie KaufmannCNRS & Univ. Lille (CRIStAL)Verified email at inria.fr
Adel JavanmardProfessor, University of Southern CaliforniaVerified email at usc.edu
Omid HatamiPhD student, University of CambridgeVerified email at cam.ac.uk
Saieed AkbariProfessor of Mathematics, Sharif University of TechnologyVerified email at sharif.edu
Etienne BoursierINRIA SaclayVerified email at inria.fr
Vianney PerchetCrest, ENSAE & Criteo AI LabVerified email at normalesup.org
Roman VershyninProfessor of Mathematics, University of California, IrvineVerified email at uci.edu
Cristiane M. SatoFederal University of de ABC Region, BrazilVerified email at ufabc.edu.br

Abbas Mehrabian

Google DeepMind

Verified email at deepmind.com - Homepage

Reinforcement Learning Bandit algorithms Machine Learning Theory


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks PL Bartlett, N Harvey, C Liaw, A Mehrabian Journal of Machine Learning Research 20 (63), 1-17, 2019	669	2019
The total variation distance between high-dimensional Gaussians with the same mean L Devroye, A Mehrabian, T Reddad arXiv preprint arXiv:1810.08693, 2018	269	2018
Nearly tight sample complexity bounds for learning mixtures of gaussians via sample compression schemes H Ashtiani, S Ben-David, N Harvey, C Liaw, A Mehrabian, Y Plan Advances in Neural Information Processing Systems 31, 2018	129*	2018
A practical algorithm for multiplayer bandits when arm means vary among players A Mehrabian, E Boursier, E Kaufmann, V Perchet International Conference on Artificial Intelligence and Statistics, 1211-1221, 2020	81	2020
A simple tool for bounding the deviation of random matrices on geometric sets C Liaw, A Mehrabian, Y Plan, R Vershynin Geometric Aspects of Functional Analysis: Israel Seminar (GAFA) 2014–2016 …, 2017	74	2017
Regret bounds for batched bandits H Esfandiari, A Karbasi, A Mehrabian, V Mirrokni Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 7340-7348, 2021	71	2021
A bounded budget network creation game S Ehsani, SS Fadaee, MA Fazli, A Mehrabian, SS Sadeghabad, M Safari, ... ACM Transactions on Algorithms (TALG) 11 (4), 1-25, 2015	58	2015
Multiplayer bandits without observing collision information G Lugosi, A Mehrabian Mathematics of Operations Research 47 (2), 1247-1265, 2022	55	2022
On the push&pull protocol for rumour spreading H Acan, A Collevecchio, A Mehrabian, N Wormald Proceedings of the 2015 ACM Symposium on Principles of Distributed Computing …, 2015	41	2015
Zero-sum flows in regular graphs S Akbari, A Daemi, O Hatami, A Javanmard, A Mehrabian Graphs and combinatorics 26, 603-615, 2010	40	2010
The capture time of grids A Mehrabian Discrete Mathematics 311, 102--105, 2010	38	2010
The minimax learning rates of normal and Ising undirected graphical models L Devroye, A Mehrabian, T Reddad	35	2020
Old dog learns new tricks: Randomized ucb for bandit problems S Vaswani, A Mehrabian, A Durand, B Kveton arXiv preprint arXiv:1910.04928, 2019	33	2019
Sample-efficient learning of mixtures H Ashtiani, S Ben-David, A Mehrabian Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018	32	2018
Chasing a fast robber on planar graphs and random graphs N Alon, A Mehrabian Journal of Graph Theory 78 (2), 81-96, 2015	30	2015
On a generalization of Meyniel's conjecture on the cops and robbers game N Alon, A Mehrabian the electronic journal of combinatorics 18 (1), P19, 2011	30	2011
On longest paths and diameter in random Apollonian networks E Ebrahimzadeh, L Farczadi, P Gao, A Mehrabian, CM Sato, N Wormald, ... Random structures & algorithms 45 (4), 703-725, 2014	28	2014
Lower bounds for the cop number when the robber is fast A Mehrabian Combinatorics, Probability and Computing 20 (4), 617-621, 2011	21	2011
Batched multi-armed bandits with optimal regret H Esfandiari, A Karbasi, A Mehrabian, V Mirrokni arXiv preprint arXiv:1910.04959, 2019	16	2019
Some techniques in density estimation H Ashtiani, A Mehrabian arXiv preprint arXiv:1801.04003, 2018	12	2018

The system can't perform the operation now. Try again later.

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors