Google Publications

•    

  Large-Scale Learning with Less RAM via Randomization

  Daniel Golovin, D. Sculley, H. Brendan McMahan, Michael Young

  Proceedings of the 30 International Conference on Machine Learning (ICML) (2013), pp. 10

•    

  No-Regret Algorithms for Unconstrained Online Convex Optimization

  Matthew Streeter, H. Brendan McMahan

  Advances in Neural Information Processing Systems (NIPS) (2012)

•    

  Open Problem: Better Bounds for Online Logistic Regression

  H. Brendan McMahan, Matthew Streeter

  COLT/ICML Joint Open Problem Session, JMLR: Workshop and Conference Proceedings (2012)

•    

  Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization

  H. Brendan McMahan

  Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS) (2011)

•    

  Adaptive Bound Optimization for Online Convex Optimization

  H. Brendan McMahan, Matthew Streeter

  Proceedings of the 23rd Annual Conference on Learning Theory (COLT) (2010)

•   

  Sleeping Experts and Bandits with Stochastic Action Availability and Adversarial Rewards

  Varun Kanade, H. Brendan McMahan, Brent Bryan

  Proceedings of the 12th International Conference on Artificial Intelligence and Statistic (AISTATS) (2009)

•   

  Tighter Bounds for Multi-Armed Bandits with Expert Advice

  H. Brendan McMahan, Matthew Streeter

  Proceedings of the 22nd Annual Conference on Learning Theory (COLT) (2009)

•  

  Robust Submodular Observation Selection

  Andreas Krause, H. Brendan McMahan, Carlos Guestrin, Anupam Gupta

  Journal of Machine Learning Research (JMLR), vol. 9 (2008), pp. 2761-2801

•   

  Efficiently Computing Minimax Expected-Size Confidence Regions

  Brent Bryan, H. Brendan McMahan, Chad M. Schafer, Jeff Schneider

  Proc. 24th ICML, ACM, Corvalis (2007), pp. 97-104

•   

  Selecting Observations Against Adversarial Objectives

  Andreas Krause, H. Brendan McMahan, Carlos Guestrin, Anupam Gupta

  Advances in Neural Information Processing Systems (NIPS 2007)

Previous Publications

•  

  A Fast Bundle-based Anytime Algorithm for Poker and other Convex Games

  H. Brendan McMahan, Geoffrey J. Gordon

  Proceedings of the 11th International Conference on Artificial Intelligence and Statistics (AISTATS) (2007)

•  

  A Unification of Extensive-Form Games and Markov Decision Processes

  H. Brendan McMahan, Geoffrey J. Gordon

  AAAI 2007

•  

  Robust Planning in Domains with Stochastic Outcomes, Adversaries, and Partial Observability

  H. Brendan McMahan

  CMU (2006)

•   

  Bounded Real-Time Dynamic Programming: RTDP with monotone upper bounds and performance guarantees

  H. Brendan McMahan, Maxim Likhachev, Geoffrey J. Gordon

  Proceedings of the 22nd International Conference on Machine Learning (ICML) (2005)

•   

  Fast Exact Planning in Markov Decision Processes

  H. Brendan McMahan, Geoffrey J. Gordon

  International Conference on Automated Planning and Scheduling (ICAPS) (2005)

•   

  Generalizing Dijkstra's algorithm and Gaussian Elimination for solving MDPs

  H. Brendan McMahan, Geoffrey J. Gordon

  Carnegie Mellon University (2005)

•   

  Online convex optimization in the bandit setting: gradient descent without a gradient

  Abraham Flaxman, Adam Tauman Kalai, H. Brendan McMahan

  Proceedings of the Sixteenth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA) (2005)

•   

  Online Geometric Optimization in the Bandit Setting Against an Adaptive Adversary

  H. Brendan McMahan, Avrim Blum

  Proceedings of the Seventeenth Annual Conference on Learning Theory (COLT) (2004), pp. 109-123

•   

  Multi-source spanning trees: algorithms for minimizing source eccentricities

  H. Brendan McMahan, A. Proskurowski

  Discrete Applied Mathematics, vol. 137/2 (2003), pp. 213-222

•   

  Planning in the Presence of Cost Functions Controlled By An Adversary

  H. Brendan McMahan, Geoffrey J. Gordon, Avrim Blum

  In Proceedings of the 20th International Conference on Machine Learning (ICML) (2003)