JL
John Langford
cs.LGstat.MLcs.AIcs.CLcs.ROcs.CVmath.OCcs.CRmath.STstat.TH
On Valency
published · living versionsW_hktak6f3·v1 · currentpublished
Off-policy evaluation for slate recommendation
with Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík +2
1 version
Preprints & journals
94 papers in the corpus · 2000–2026Hierarchical Latent Prediction for Language Models2608.05806v1 · Chang Shi, Tim Pearce, Manan Tomar et al.2026 · 0 citationsarXiv
MEMENTO: Teaching LLMs to Manage Their Own Context2604.09852v1 · Vasilis Kontonis, Yuchen Zeng, Shivam Garg et al.2026 · 0 citationsarXiv
When Does Predictive Inverse Dynamics Outperform Behavior Cloning?2601.21718v3 · Lukas Schafer, Pallavi Choudhury, Abdelhak Lemkhenter et al.2026 · 0 citationsarXiv
Next-Latent Prediction Transformers Learn Compact World Models2511.05963v4 · Jayden Teoh, Manan Tomar, Kwangjun Ahn et al.2025 · 0 citationsarXiv
Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead2504.00294v1 · Vidhisha Balachandran, Jingya Chen, Lingjiao Chen et al.2025 · 0 citationsarXiv
Efficient Joint Prediction of Multiple Future Tokens2503.21801v1 · Kwangjun Ahn, Alex Lamb, John Langford2025 · 0 citationsarXiv
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles2410.04571v3 · Aakriti Agrawal, Mucong Ding, Zora Che et al.2024 · 1 citationarXiv
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization2409.18433v2 · Mucong Ding, Chenghao Deng, Jocelyn Choo et al.2024 · 4 citationsarXiv
Video Occupancy Models2407.09533v1 · Manan Tomar, Philippe Hansen-Estruch, Philip Bachman et al.2024 · 0 citationsarXiv
Towards Principled Representation Learning from Videos for Reinforcement Learning2403.13765v1 · Dipendra Misra, Akanksha Saran, Tengyang Xie et al.2024 · 1 citationarXiv
Position Paper: Agent AI Towards a Holistic Intelligence2403.00833v1 · Qiuyuan Huang, Naoki Wake, Bidipta Sarkar et al.2024 · 12 citationsarXiv
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss2402.06187v4 · Ruijie Zheng, Yongyuan Liang, Xiyao Wang et al.2024 · 1 citationarXiv
PcLast: Discovering Plannable Continuous Latent States2311.03534v2 · Anurag Koul, Shivakanth Sujit, Shaoru Chen et al.2023 · 0 citationsarXiv
EyeO: Autocalibrating Gaze Output with Gaze Input2307.15039v2 · Akanksha Saran, Jacob Alber, Cyril Zhang et al.2023 · 0 citationsarXiv
Streaming Active Learning with Deep Neural Networks2303.02535v2 · Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy et al.2023 · 4 citationsarXiv
Towards Data-Driven Offline Simulations for Online Reinforcement Learning2211.07614v1 · Shengpu Tang, Felipe Vieira Frujeri, Dipendra Misra et al.2022 · 0 citationsarXiv
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information2211.00164v2 · Riashat Islam, Manan Tomar, Alex Lamb et al.2022 · 1 citationarXiv
Eigen Memory Trees2210.14077v3 · Mark Rucker, Jordan T. Ash, John Langford et al.2022 · 0 citationsarXiv
Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models2207.08229v2 · Alex Lamb, Riashat Islam, Yonathan Efroni et al.2022 · 1 citationarXiv
Contextual Bandits with Large Action Spaces: Made Practical2207.05836v1 · Yinglun Zhu, Dylan J. Foster, John Langford et al.2022 · 1 citationarXiv
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information2206.04282v1 · Yonathan Efroni, Dylan J. Foster, Dipendra Misra et al.2022 · 2 citationsarXiv
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning2202.05318v2 · Alberto Bietti, Chen-Yu Wei, Miroslav Dud'ik et al.2022 · 24 citationsarXiv
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics2110.08847v2 · Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy et al.2021 · 3 citationsarXiv
ChaCha for Online AutoML2106.04815v2 · Qingyun Wu, Chi Wang, John Langford et al.2021 · 0 citationsICML 2021
Interaction-Grounded Learning2106.04887v2 · Tengyang Xie, John Langford, Paul Mineiro et al.2021 · 1 citationarXiv
Resonance: Replacing Software Constants with Context-Aware Models in Real-time Communication2011.12715v1 · Jayant Gupchup, Ashkan Aazami, Yaran Fan et al.2020 · 1 citationML for Systems, NeurIPS 2020
Learning the Linear Quadratic Regulator from Nonlinear Observations2010.03799v1 · Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz et al.2020 · 4 citationsarXiv
Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting2006.07507v3 · Keyi Chen, John Langford, Francesco Orabona2020 · 3 citationsarXiv
Efficient Contextual Bandits with Continuous Actions2006.06040v2 · Maryam Majzoubi, Chicheng Zhang, Rajan Chari et al.2020 · 9 citationsarXiv
PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing2004.03544v4 · Justin Chan, Dean Foster, Shyam Gollakota et al.2020 · 157 citationsarXiv
Federated Residual Learning2003.12880v1 · Alekh Agarwal, John Langford, Chen-Yu Wei2020 · 19 citationsarXiv
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning1911.05815v1 · Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy et al.2019 · 49 citationsarXiv
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds1906.03671v2 · Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy et al.2019 · 418 citations2020 International Conference on Learning Representations
Empirical Likelihood for Contextual Bandits1906.03323v4 · Nikos Karampatziakis, John Langford, Paul Mineiro2019 · 6 citationsarXiv
Efficient Forward Architecture Search1905.13360v1 · Hanzhang Hu, John Langford, Rich Caruana et al.2019 · 22 citationsarXiv
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting1902.01520v4 · Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins et al.2019 · 25 citationsarXiv
Provably efficient RL with Rich Observations via Latent State Decoding1901.09018v3 · Simon S. Du, Akshay Krishnamurthy, Nan Jiang et al.2019 · 67 citationsarXiv
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback1901.00301v2 · Chicheng Zhang, Alekh Agarwal, Hal Daum'e III et al.2019 · 14 citationsarXiv
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches1811.08540v3 · Wen Sun, Nan Jiang, Akshay Krishnamurthy et al.2018 · 67 citationsarXiv
Contextual Memory Trees1807.06473v3 · Wen Sun, Alina Beygelzimer, Hal Daum'e III et al.2018 · 3 citationsarXiv
A Reductions Approach to Fair Classification1803.02453v3 · Alekh Agarwal, Alina Beygelzimer, Miroslav Dud'ik et al.2018 · 364 citationsarXiv
On Oracle-Efficient PAC RL with Rich Observations1803.00606v4 · Christoph Dann, Nan Jiang, Akshay Krishnamurthy et al.2018 · 25 citationsarXiv
A Contextual Bandit Bake-off1802.04064v5 · Alberto Bietti, Alekh Agarwal, John Langford2018 · 65 citationsarXiv
Efficient Contextual Bandits in Non-stationary Worlds1708.01799v4 · Haipeng Luo, Chen-Yu Wei, Alekh Agarwal et al.2017 · 100 citationsarXiv
Learning Deep ResNet Blocks Sequentially using Boosting Theory1706.04964v4 · Furong Huang, Jordan Ash, John Langford et al.2017 · 77 citationsarXiv
Mapping Instructions and Visual Observations to Actions with Reinforcement Learning1704.08795v2 · Dipendra Misra, John Langford, Yoav Artzi2017 · 188 citationsarXiv
Active Learning for Cost-Sensitive Classification1703.01014v4 · Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang et al.2017 · 49 citationsJournal of Machine Learning Research, 2019
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable1610.09512v2 · Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal et al.2016 · 144 citationsarXiv
Logarithmic Time One-Against-Some1606.04988v2 · Hal Daume III, Nikos Karampatziakis, John Langford et al.2016 · 27 citationsarXiv
Making Contextual Decisions with Low Technical Debt1606.03966v2 · Alekh Agarwal, Sarah Bird, Markus Cozowicz et al.2016 · 70 citationsarXivon Valency
Career total: 204 works. 94 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.