Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for John Langford

Provable RL with Exogenous Distractors via Multistep Inverse Dynamics


Oct 17, 2021
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford


  Access Paper or Ask Questions

ChaCha for Online AutoML


Jun 11, 2021
Qingyun Wu, Chi Wang, John Langford, Paul Mineiro, Marco Rossi

* ICML 2021 
* 16 pages (including supplementary appendix). Appearing at ICML 2021 

  Access Paper or Ask Questions

Interaction-Grounded Learning


Jun 09, 2021
Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad

* Published in ICML 2021 

  Access Paper or Ask Questions

Resonance: Replacing Software Constants with Context-Aware Models in Real-time Communication


Nov 23, 2020
Jayant Gupchup, Ashkan Aazami, Yaran Fan, Senja Filipi, Tom Finley, Scott Inglis, Marcus Asteborg, Luke Caroll, Rajan Chari, Markus Cozowicz, Vishak Gopal, Vinod Prakash, Sasikanth Bendapudi, Jack Gerrits, Eric Lau, Huazhou Liu, Marco Rossi, Dima Slobodianyk, Dmitri Birjukov, Matty Cooper, Nilesh Javar, Dmitriy Perednya, Sriram Srinivasan, John Langford, Ross Cutler, Johannes Gehrke

* Workshop on ML for Systems at NeurIPS 2020, Accepted 

  Access Paper or Ask Questions

Learning the Linear Quadratic Regulator from Nonlinear Observations


Oct 08, 2020
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford

* To appear at NeurIPS 2020 

  Access Paper or Ask Questions

Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting


Jun 12, 2020
Keyi Chen, John Langford, Francesco Orabona


  Access Paper or Ask Questions

Efficient Contextual Bandits with Continuous Actions


Jun 10, 2020
Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins


  Access Paper or Ask Questions

Federated Residual Learning


Mar 28, 2020
Alekh Agarwal, John Langford, Chen-Yu Wei


  Access Paper or Ask Questions

Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning


Nov 13, 2019
Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford


  Access Paper or Ask Questions

Empirical Likelihood for Contextual Bandits


Jun 21, 2019
Nikos Karampatziakis, John Langford, Paul Mineiro


  Access Paper or Ask Questions

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds


Jun 09, 2019
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal


  Access Paper or Ask Questions

Efficient Forward Architecture Search


May 31, 2019
Hanzhang Hu, John Langford, Rich Caruana, Saurajit Mukherjee, Eric Horvitz, Debadeepta Dey

* preprint 

  Access Paper or Ask Questions

Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting


Feb 05, 2019
Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang


  Access Paper or Ask Questions

Provably efficient RL with Rich Observations via Latent State Decoding


Jan 25, 2019
Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford


  Access Paper or Ask Questions

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


Jan 02, 2019
Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand N Negahban

* 43 pages, 21 figures 

  Access Paper or Ask Questions

Model-Based Reinforcement Learning in Contextual Decision Processes


Nov 21, 2018
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford

* 30 

  Access Paper or Ask Questions

On Oracle-Efficient PAC RL with Rich Observations


Oct 31, 2018
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire

* appearing at NIPS 18; full paper including appendix 

  Access Paper or Ask Questions

Contextual Memory Trees


Jul 17, 2018
Wen Sun, Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro


  Access Paper or Ask Questions

A Reductions Approach to Fair Classification


Jul 16, 2018
Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, Hanna Wallach


  Access Paper or Ask Questions

Learning Deep ResNet Blocks Sequentially using Boosting Theory


Jun 14, 2018
Furong Huang, Jordan Ash, John Langford, Robert Schapire

* Accepted to ICML 2018 

  Access Paper or Ask Questions

Efficient Contextual Bandits in Non-stationary Worlds


Jun 07, 2018
Haipeng Luo, Chen-Yu Wei, Alekh Agarwal, John Langford


  Access Paper or Ask Questions

A Contextual Bandit Bake-off


May 30, 2018
Alberto Bietti, Alekh Agarwal, John Langford


  Access Paper or Ask Questions

Active Learning for Cost-Sensitive Classification


Nov 13, 2017
Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daume III, John Langford


  Access Paper or Ask Questions

Off-policy evaluation for slate recommendation


Nov 06, 2017
Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík, John Langford, Damien Jose, Imed Zitouni

* 31 pages (9 main paper, 20 supplementary), 12 figures (2 main paper, 10 supplementary) 

  Access Paper or Ask Questions

Efficient Second Order Online Learning by Sketching


Oct 17, 2017
Haipeng Luo, Alekh Agarwal, Nicolo Cesa-Bianchi, John Langford


  Access Paper or Ask Questions

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning


Jul 22, 2017
Dipendra Misra, John Langford, Yoav Artzi

* In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2017 

  Access Paper or Ask Questions

Making Contextual Decisions with Low Technical Debt


May 09, 2017
Alekh Agarwal, Sarah Bird, Markus Cozowicz, Luong Hoang, John Langford, Stephen Lee, Jiaji Li, Dan Melamed, Gal Oshri, Oswaldo Ribas, Siddhartha Sen, Alex Slivkins


  Access Paper or Ask Questions

Contextual Decision Processes with Low Bellman Rank are PAC-Learnable


Dec 01, 2016
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire

* 42 pages, 1 figure 

  Access Paper or Ask Questions