Alekh Agarwal

发表

Off-Policy Policy Gradient with State Distribution Correction pdf

Emma Brunskill, Yao Liu, Adith Swaminathan, 2019, UAI 2019.

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds pdf

John Langford, Alekh Agarwal, Jordan T. Ash, 2019, ICLR.

Distributed delayed stochastic optimization

John C. Duchi, Alekh Agarwal, Alekh Agarwal, 2011, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization

Prateek Jain, Praneeth Netrapalli, Animashree Anandkumar, 2013, SIAM J. Optim..

Hierarchical Imitation and Reinforcement Learning pdf

Nan Jiang, Yisong Yue, Miroslav Dudík, 2018, ICML.

Message-passing for Graph-structured Linear Programs: Proximal Methods and Rounding Schemes

Martin J. Wainwright, Pradeep Ravikumar, Alekh Agarwal, 2010, J. Mach. Learn. Res..

On Oracle-Efficient PAC RL with Rich Observations

Nan Jiang, John Langford, Akshay Krishnamurthy, 2018, NeurIPS.

Robust Multi-objective Learning with Mentor Feedback

Miroslav Dudík, Aleksandrs Slivkins, Robert E. Schapire, 2014, COLT.

Fast global convergence of gradient methods for high-dimensional statistical recovery pdf

Martin J. Wainwright, Alekh Agarwal, Sahand N. Negahban, 2011, ArXiv.

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning pdf

Wen Sun, Alekh Agarwal, Mikael Henaff, 2020, NeurIPS.

Safe Reinforcement Learning via Curriculum Induction pdf

Andrey Kolobov, Alekh Agarwal, Andreas Krause, 2020, NeurIPS.

Taking a hint: How to leverage loss predictors in contextual bandits? pdf

Haipeng Luo, Chen-Yu Wei, Alekh Agarwal, 2020, COLT.

Policy Improvement from Multiple Experts pdf

Andrey Kolobov, Ching-An Cheng, Alekh Agarwal, 2020, ArXiv.

A reliable effective terascale linear learning system

John Langford, Miroslav Dudík, Alekh Agarwal, 2011, J. Mach. Learn. Res..

Matrix regularization techniques for online multitask learning

Peter L. Bartlett, Alekh Agarwal, Alexander Rakhlin, 2008 .

Efficient Contextual Semi-Bandit Learning pdf

Akshay Krishnamurthy, Miroslav Dudík, Alekh Agarwal, 2015, ArXiv.

A Lower Bound for the Optimization of Finite Sums

Léon Bottou, Alekh Agarwal, L. Bottou, 2014, ICML.

A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries

Praneeth Netrapalli, Animashree Anandkumar, Alekh Agarwal, 2013, IEEE Transactions on Information Theory.

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

Sham M. Kakade, Jason D. Lee, Gaurav Mahajan, 2019, J. Mach. Learn. Res..

Computational Trade-offs in Statistical Learning

Alekh Agarwal, Alekh Agarwal, 2012 .

Corralling a Band of Bandit Algorithms pdf

Haipeng Luo, Robert E. Schapire, Behnam Neyshabur, 2016, COLT.

Distributed Dual Averaging In Networks

Martin J. Wainwright, John C. Duchi, Alekh Agarwal, 2010, NIPS.

Learning random walks to rank nodes in graphs

Soumen Chakrabarti, Alekh Agarwal, Alekh Agarwal, 2007, ICML '07.

On Oracle-Efficient PAC Reinforcement Learning with Rich Observations

Nan Jiang, John Langford, Akshay Krishnamurthy, 2018 .

Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration

Emma Brunskill, Adith Swaminathan, Alekh Agarwal, 2020, NeurIPS.

FASt global convergence of gradient methods for solving regularized M-estimation

Martin J. Wainwright, Alekh Agarwal, Sahand N. Negahban, 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).

Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback pdf

John Langford, Hal Daumé, Alekh Agarwal, 2019, ICML.

Stochastic optimization and sparse statistical recovery: An optimal algorithm for high dimensions

Martin J. Wainwright, Alekh Agarwal, Sahand N. Negahban, 2012, 2014 48th Annual Conference on Information Sciences and Systems (CISS).

Efficient and Parsimonious Agnostic Active Learning

John Langford, Robert E. Schapire, Tzu-Kuo Huang, 2015, NIPS.

Survey of some new convergence analysis techniques for sum and max belief propagation on loopy graphs

Alekh Agarwal, 2007 .

Learning with Missing Features

Peter L. Bartlett, Afshin Rostamizadeh, Alekh Agarwal, 2011, UAI.

On the Optimality of Sparse Model-Based Planning for Markov Decision Processes pdf

Lin F. Yang, Alekh Agarwal, Sham Kakade, 2019, ArXiv.

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs pdf

Akshay Krishnamurthy, Wen Sun, Alekh Agarwal, 2020, NeurIPS.

An Analysis of Inference with the Universum

Bernhard Schölkopf, Alekh Agarwal, Olivier Chapelle, 2007, NIPS.

Off-Policy Policy Gradient with Stationary Distribution Correction

Yao Liu, Emma Brunskill, Adith Swaminathan, 2019, UAI.

A Contextual Bandit Bake-off

John Langford, Alekh Agarwal, Alberto Bietti, 2018, J. Mach. Learn. Res..

Fair Regression: Quantitative Definitions and Reduction-based Algorithms

Miroslav Dudík, Zhiwei Steven Wu, Alekh Agarwal, 2019, ICML.

Practical Contextual Bandits with Regression Oracles pdf

Haipeng Luo, Miroslav Dudík, Robert E. Schapire, 2018, ICML.

Fast global convergence rates of gradient methods for high-dimensional statistical recovery

Martin J. Wainwright, Alekh Agarwal, Sahand N. Negahban, 2010, NIPS.

Optimal and Adaptive Off-policy Evaluation in Contextual Bandits pdf

Miroslav Dudík, Yu-Xiang Wang, Alekh Agarwal, 2016, ICML.

Ergodic mirror descent

Michael I. Jordan, John C. Duchi, Alekh Agarwal, 2011, 2011 49th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Optimal Allocation Strategies for the Dark Pool Problem

Peter L. Bartlett, Alekh Agarwal, Max Dama, 2010, AISTATS.

Off-policy evaluation for slate recommendation

John Langford, Akshay Krishnamurthy, Miroslav Dudík, 2016, NIPS.

Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions

Martin J. Wainwright, Alekh Agarwal, Sahand N. Negahban, 2011, ICML.

Learning Parameters in Entity Relationship Graphs from Ranking Preferences

Soumen Chakrabarti, Alekh Agarwal, Alekh Agarwal, 2006, PKDD.

Oracle inequalities for computationally adaptive model selection pdf

Peter L. Bartlett, John C. Duchi, Alekh Agarwal, 2012, ArXiv.

Policy Improvement via Imitation of Multiple Oracles

Andrey Kolobov, Ching-An Cheng, Alekh Agarwal, 2020, NeurIPS.

A Stochastic View of Optimal Regret through Minimax Duality pdf

Peter L. Bartlett, Alekh Agarwal, Jacob D. Abernethy, 2009, COLT.

Open Problem: The Dependence of Sample Complexity Lower Bounds on Planning Horizon

Nan Jiang, Alekh Agarwal, Alekh Agarwal, 2018, COLT.

On Polynomial Time PAC Reinforcement Learning with Rich Observations pdf

Nan Jiang, John Langford, Akshay Krishnamurthy, 2018, ArXiv.

Contextual Bandit Learning with Predictable Rewards pdf

John Langford, Miroslav Dudík, Robert E. Schapire, 2012, AISTATS.

Provably Good Batch Reinforcement Learning Without Great Exploration pdf

Emma Brunskill, Adith Swaminathan, Alekh Agarwal, 2020, ArXiv.

Learning to rank networked entities

Soumen Chakrabarti, Alekh Agarwal, Sunny Aggarwal, 2006, KDD '06.

Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal

Lin F. Yang, Alekh Agarwal, Sham Kakade, 2019, COLT 2020.

Learning to Search Better than Your Teacher pdf

John Langford, Akshay Krishnamurthy, Kai-Wei Chang, 2015, ICML.

The Generalization Ability of Online Algorithms for Dependent Data

John C. Duchi, Alekh Agarwal, Alekh Agarwal, 2011, IEEE Transactions on Information Theory.

A Reductions Approach to Fair Classification pdf

John Langford, Miroslav Dudík, Hanna M. Wallach, 2018, ICML.

Practical Evaluation and Optimization of Contextual Bandit Algorithms pdf

John Langford, Alekh Agarwal, Alberto Bietti, 2018, ArXiv.

Efficient Contextual Bandits in Non-stationary Worlds pdf

Haipeng Luo, Alekh Agarwal, John Langford, 2017, COLT.

Model-Based Reinforcement Learning in Contextual Decision Processes pdf

Nan Jiang, John Langford, Akshay Krishnamurthy, 2018, ArXiv.

Active Learning for Cost-Sensitive Classification

John Langford, Akshay Krishnamurthy, Tzu-Kuo Huang, 2017, ICML.

Ergodic Subgradient Descent

Michael I. Jordan, John C. Duchi, Alekh Agarwal, 2011 .

Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling

Martin J. Wainwright, John C. Duchi, Alekh Agarwal, 2010, IEEE Transactions on Automatic Control.

Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains pdf

Fernando Diaz, Akshay Krishnamurthy, Robert E. Schapire, 2016, ArXiv.

Para-active learning pdf

John Langford, Miroslav Dudík, Léon Bottou, 2013, ArXiv.

Federated Residual Learning pdf

Chen-Yu Wei, Alekh Agarwal, John Langford, 2020, ArXiv.

Augmenting WordNet with Polarity Information on Adjectives

Pushpak Bhattacharyya, Alekh Agarwal, Alekh Agarwal, 2006 .

Information-theoretic lower bounds on the oracle complexity of convex optimization

Martin J. Wainwright, Pradeep Ravikumar, Peter L. Bartlett, 2009, NIPS.

PAC Reinforcement Learning with Rich Observations

John Langford, Akshay Krishnamurthy, Alekh Agarwal, 2016, NIPS.

Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations

Eric Horvitz, Sean Andrist, Debadeepta Dey, 2019, AAAI.

Open Problem: First-Order Regret Bounds for Contextual Bandits

John Langford, Haipeng Luo, Akshay Krishnamurthy, 2017, COLT.

Selective sampling algorithms for cost-sensitive multiclass prediction

Alekh Agarwal, Alekh Agarwal, 2013, ICML.

Making Contextual Decisions with Low Technical Debt

John Langford, Stephen Lee, Siddhartha Sen, 2016 .

Contextual Decision Processes with low Bellman rank are PAC-Learnable pdf

Nan Jiang, John Langford, Akshay Krishnamurthy, 2016, ICML.

Message-passing for graph-structured linear programs: proximal projections, convergence and rounding schemes

Martin J. Wainwright, Pradeep Ravikumar, Alekh Agarwal, 2008, ICML '08.

Dual averaging for distributed optimization

Martin J. Wainwright, John C. Duchi, Alekh Agarwal, 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Scalable Non-linear Learning with Adaptive Polynomial Expansions

John Langford, Matus Telgarsky, Alekh Agarwal, 2014, NIPS.

Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

Eric Horvitz, Ashish Kapoor, Stefano Ermon, 2019, DGS@ICLR.

Fast Convergence of Regularized Learning in Games

Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, 2015, NIPS.

Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback.

Lin Xiao, Alekh Agarwal, Ofer Dekel, 2010, COLT 2010.

Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization

Martin J. Wainwright, Pradeep Ravikumar, Peter L. Bartlett, 2010, IEEE Transactions on Information Theory.

Reparameterized Variational Divergence Minimization for Stable Imitation pdf

Asli Çelikyilmaz, Debadeepta Dey, William B. Dolan, 2020, ArXiv.

Oracle inequalities for computationally budgeted model selection

Peter L. Bartlett, John C. Duchi, Alekh Agarwal, 2011, COLT.

Learning Sparsely Used Overcomplete Dictionaries

Prateek Jain, Anima Anandkumar, Praneeth Netrapalli, 2014, COLT.

Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches

Nan Jiang, John Langford, Akshay Krishnamurthy, 2018, COLT.

Efficient Second Order Online Learning by Sketching

Haipeng Luo, Nicolò Cesa-Bianchi, Alekh Agarwal, 2016, NIPS.

Contextual-MDPs for PAC-Reinforcement Learning with Rich Observations pdf

John Langford, Akshay Krishnamurthy, Alekh Agarwal, 2016, ArXiv.

Contextual semibandits via supervised learning oracles

Akshay Krishnamurthy, Miroslav Dudík, Alekh Agarwal, 2015, NIPS.

Least Squares Revisited: Scalable Approaches for Multi-class Prediction

Le Song, Nikos Karampatziakis, Sham M. Kakade, 2013, ICML.

Provably efficient RL with Rich Observations via Latent State Decoding pdf

Nan Jiang, John Langford, Akshay Krishnamurthy, 2019, ICML.

Stochastic Convex Optimization with Bandit Feedback

Sham M. Kakade, Dean P. Foster, Alekh Agarwal, 2011, SIAM J. Optim..

A Multiworld Testing Decision Service pdf

John Langford, Stephen Lee, Siddhartha Sen, 2016, ArXiv.

Exact Recovery of Sparsely Used Overcomplete Dictionaries pdf

Anima Anandkumar, Praneeth Netrapalli, Alekh Agarwal, 2013, ArXiv.

Matrix regularization techniques for online multitask learning [Technical Report No. UCB/EECS-2008-138]

Peter L. Bartlett, Alekh Agarwal, Alexander Rakhlin, 2008 .

Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits

John Langford, Lihong Li, Robert E. Schapire, 2014, ICML.

Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation

Alekh Agarwal, Andrea Zanette, Ching-An Cheng, 2021, COLT.

Towards a Dimension-Free Understanding of Adaptive Linear Control

Max Simchowitz, Alekh Agarwal, Peter Bartlett, 2021, COLT.

Bellman-consistent Pessimism for Offline Reinforcement Learning pdf

Paul Mineiro, Nan Jiang, Alekh Agarwal, 2021, ArXiv.

Provably Correct Optimization and Exploration with Non-linear Policies

Wotao Yin, Alekh Agarwal, Fei Feng, 2021, ICML.

Provable RL with Exogenous Distractors via Multistep Inverse Dynamics pdf

John Langford, Akshay Krishnamurthy, Alekh Agarwal, 2021, ArXiv.

Model-free Representation Learning and Exploration in Low-rank MDPs pdf

Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, 2021, ArXiv.

Policy Improvement via Imitation of Multiple Oracles

Andrey Kolobov, Ching-An Cheng, Alekh Agarwal, 2020, NeurIPS.