About
Discord Stateoftheart AI
GitHub

Publications

199

Cited by

6591

Alekh Agarwal

machine learning
Microsoft

United States

Papers and Citations

1 - 50
Dual averaging for distributed optimization: Convergence analysis and network scaling
2011
John Duchi
Martin Wainwright
Alekh Agarwal
Cited by 941
Distributed delayed stochastic optimization
2011
Alekh Agarwal
John Duchi
Cited by 482
A Reliable Effective Terascale Linear Learning System
2011
Miroslav Dudik
John Langford
Alekh Agarwal
+1
Cited by 361
A reductions approach to fair classification
2018
Alina Beygelzimer
Miroslav Dudik
Alekh Agarwal
+4
Cited by 359
Taming the monster: A fast and simple algorithm for contextual bandits
2014
Lihong Li
Satyen Kale
Daniel Hsu
+4
Cited by 323
Fast global convergence rates of gradient methods for high-dimensional statistical recovery
2010
Martin Wainwright
Sahand Negahban
Alekh Agarwal
Cited by 316
Information-theoretic lower bounds on the oracle complexity of convex optimization
2009
Alekh Agarwal
Martin Wainwright
Peter Bartlett
+1
Cited by 292
Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback.
2010
Lin Xiao
Alekh Agarwal
Ofer Dekel
Cited by 268
Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions
2012
Sahand Negahban
Martin Wainwright
Alekh Agarwal
Cited by 259
Fast global convergence of gradient methods for high-dimensional statistical recovery
2012
Martin Wainwright
Alekh Agarwal
Sahand Negahban
Cited by 221
Learning to search better than your teacher
2015
Hal Daume
John Langford
Alekh Agarwal
+3
Cited by 173
Learning sparsely used overcomplete dictionaries via alternating minimization
2016
Anima Anandkumar
Prateek Jain
Praneeth Netrapalli
+1
Cited by 158
Contextual decision processes with low bellman rank are pac-learnable
2016
Alekh Agarwal
Robert Schapire
John Langford
+2
Cited by 145
Learning to rank networked entities
2006
Soumen Chakrabarti
Alekh Agarwal
S Aggarwal
Cited by 134
SUPPLEMENTARY MATERIAL: FAST GLOBAL CONVERGENCE OF GRADIENT METHODS FOR HIGH-DIMENSIONAL STATISTICAL RECOVERY
2010
Martin Wainwright
Alekh Agarwal
Sahand Negahban
Cited by 121
Optimality and approximation with policy gradient methods in markov decision processes
2019
Alekh Agarwal
Jason D. Lee
Gaurav Mahajan
+1
Cited by 118
Stochastic convex optimization with bandit feedback
2011
Sham M Kakade
Alexander Rakhlin
Alekh Agarwal
+3
Cited by 116
Message-passing for graph-structured linear programs: Proximal methods and rounding schemes
2010
Pradeep Ravikumar
Alekh Agarwal
Martin Wainwright
Cited by 115
A lower bound for the optimization of finite sums
2015
Leon Bottou
Alekh Agarwal
Cited by 113
Learning sparsely used overcomplete dictionaries
2014
Praneeth Netrapalli
Alekh Agarwal
Prateek Jain
+2
Cited by 102
Fast convergence of regularized learning in games
2015
Vasilis Syrgkanis
Robert Schapire
Haipeng Luo
+1
Cited by 92
A stochastic view of optimal regret through minimax duality
2009
Peter Bartlett
Alekh Agarwal
Jacob Abernethy
+1
Cited by 91
An analysis of inference with the universum
2008
Alekh Agarwal
Bernhard Schölkopf
Fabian Sinz
+1
Cited by 85
A clustering approach to learning sparsely used overcomplete dictionaries
2016
Praneeth Netrapalli
Alekh Agarwal
Anima Anandkumar
Cited by 79
Efficient second order online learning by sketching
2016
John Langford
Haipeng Luo
Alekh Agarwal
+2
Cited by 79
Optimal and adaptive off-policy evaluation in contextual bandits
2017
Yu-Xiang Wang
Alekh Agarwal
M Dudık
Cited by 77
Hierarchical imitation and reinforcement learning
2018
Alekh Agarwal
Miroslav Dudik
Hoang M. Le
+5
Cited by 77
Learning random walks to rank nodes in graphs
2007
Soumen Chakrabarti
Alekh Agarwal
Cited by 72
Off-policy evaluation for slate recommendation
2017
John Langford
Damien Jose
Alekh Agarwal
+4
Cited by 69
Sentiment analysis: A new approach for effective use of linguistic knowledge and exploiting similarities in a set of documents to be classified
2005
P Bhattacharyya
Alekh Agarwal
Cited by 69
Corralling a band of bandit algorithms
2017
Behnam Neyshabur
Haipeng Luo
Robert Schapire
+1
Cited by 65
PAC reinforcement learning with rich observations
2016
John Langford
Akshay Krishnamurthy
Alekh Agarwal
Cited by 64
Distributed dual averaging in networks
2010
Martin Wainwright
Alekh Agarwal
John Duchi
Cited by 62
The generalization ability of online algorithms for dependent data
2012
John Duchi
Alekh Agarwal
Cited by 61
Making contextual decisions with low technical debt
2016
Gal Oshri
Sarah Bird
Alekh Agarwal
+10
Cited by 60
Off-Policy Policy Gradient with Stationary Distribution Correction
2020
Yao Liu
Y Liu
Adith Swaminathan
+2
Cited by 60
Ergodic mirror descent
2012
Alekh Agarwal
John Duchi
Mikael Johansson
+1
Cited by 60
Efficient contextual bandits in non-stationary worlds
2018
Chen-Yu Wei
Alekh Agarwal
Haipeng Luo
+1
Cited by 58
Exact recovery of sparsely used overcomplete dictionaries
2013
Praneeth Netrapalli
Anima Anandkumar
Alekh Agarwal
Cited by 52
Model-based rl in contextual decision processes: Pac bounds and exponential improvements over model-free approaches
2019
Wen Sun
Nan Jiang
Alekh Agarwal
+2
Cited by 51
A contextual bandit bake-off
2018
Alekh Agarwal
John Langford
Alberto Bietti
Cited by 50
Off-policy policy gradient with state distribution correction
2019
Emma Brunskill
Adith Swaminathan
Yao Liu
+1
Cited by 46
Selective sampling algorithms for cost-sensitive multiclass prediction
2013
Alekh Agarwal
Cited by 45
On oracle-efficient PAC RL with rich observations
2018
Robert Schapire
John Langford
Akshay Krishnamurthy
+3
Cited by 41
Provably efficient RL with Rich Observations via Latent State Decoding
2019
Akshay Krishnamurthy
Nan Jiang
John Langford
+3
Cited by 40
Exploratory gradient boosting for reinforcement learning in complex domains
2016
Robert Schapire
Akshay Krishnamurthy
Alekh Agarwal
+2
Cited by 39
Matrix regularization techniques for online multitask learning
2008
Peter Bartlett
Alexander Rakhlin
Alekh Agarwal
Cited by 38
Practical contextual bandits with regression oracles
2018
Robert Schapire
Haipeng Luo
Dylan J. Foster
+3
Cited by 38
Efficient and parsimonious agnostic active learning
2015
John Langford
Daniel Hsu
Robert Schapire
+2
Cited by 37
Bias correction of learned generative models using likelihood-free importance weighting
2019
Eric J Horvitz
Jiaming Song
Alekh Agarwal
+5
Cited by 37