Alert button
Picture for John Langford

John Langford

Alert button

Resourceful Contextual Bandits

Jul 31, 2015
Ashwinkumar Badanidiyuru, John Langford, Aleksandrs Slivkins

Viaarxiv icon

Learning to Search Better Than Your Teacher

May 20, 2015
Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé III, John Langford

Figure 1 for Learning to Search Better Than Your Teacher
Figure 2 for Learning to Search Better Than Your Teacher
Figure 3 for Learning to Search Better Than Your Teacher
Figure 4 for Learning to Search Better Than Your Teacher
Viaarxiv icon

Learning to Search for Dependencies

May 07, 2015
Kai-Wei Chang, He He, Hal Daumé III, John Langford

Figure 1 for Learning to Search for Dependencies
Figure 2 for Learning to Search for Dependencies
Figure 3 for Learning to Search for Dependencies
Figure 4 for Learning to Search for Dependencies
Viaarxiv icon

Doubly Robust Policy Evaluation and Optimization

Mar 10, 2015
Miroslav Dudík, Dumitru Erhan, John Langford, Lihong Li

Figure 1 for Doubly Robust Policy Evaluation and Optimization
Figure 2 for Doubly Robust Policy Evaluation and Optimization
Figure 3 for Doubly Robust Policy Evaluation and Optimization
Figure 4 for Doubly Robust Policy Evaluation and Optimization
Viaarxiv icon

Learning Reductions that Really Work

Feb 09, 2015
Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro

Figure 1 for Learning Reductions that Really Work
Figure 2 for Learning Reductions that Really Work
Figure 3 for Learning Reductions that Really Work
Viaarxiv icon

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

Oct 14, 2014
Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire

Figure 1 for Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Viaarxiv icon

Scalable Nonlinear Learning with Adaptive Polynomial Expansions

Oct 02, 2014
Alekh Agarwal, Alina Beygelzimer, Daniel Hsu, John Langford, Matus Telgarsky

Figure 1 for Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Figure 2 for Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Figure 3 for Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Figure 4 for Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Viaarxiv icon

Normalized Online Learning

Aug 09, 2014
Stephane Ross, Paul Mineiro, John Langford

Figure 1 for Normalized Online Learning
Figure 2 for Normalized Online Learning
Figure 3 for Normalized Online Learning
Figure 4 for Normalized Online Learning
Viaarxiv icon

Conditional Probability Tree Estimation Analysis and Algorithms

Aug 09, 2014
Alina Beygelzimer, John Langford, Yuri Lifshits, Gregory Sorkin, Alexander L. Strehl

Viaarxiv icon

Efficient Online Bootstrapping for Large Scale Learning

Dec 18, 2013
Zhen Qin, Vaclav Petricek, Nikos Karampatziakis, Lihong Li, John Langford

Figure 1 for Efficient Online Bootstrapping for Large Scale Learning
Figure 2 for Efficient Online Bootstrapping for Large Scale Learning
Figure 3 for Efficient Online Bootstrapping for Large Scale Learning
Figure 4 for Efficient Online Bootstrapping for Large Scale Learning
Viaarxiv icon