Haipeng Luo

Assistant Professor
Computer Science Department
University of Southern California

Office: SAL 216
Email: haipengl at usc dot edu


Home

Publications

CV

Miscellaneous


Preprints

Haipeng Luo, Alekh Agarwal and John Langford.
Efficient Contextual Bandits in Non-stationary Worlds. [arXiv]

Open Problems

Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo and Robert E. Schapire.
Open Problem: First-Order Regret Bounds for Contextual Bandits. [pdf]
In Proceedings of the 30th Conference on Learning Theory (COLT 2017).

PhD Thesis

Optimal and Adaptive Online Learning. [pdf] [slides]

Publications

Miroslav Dudik, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis and Jennifer Wortman Vaughan.
Oracle-Efficient Online Learning and Auction Design. [arXiv]
In the 58th Annual Symposium on Foundations of Computer Science (FOCS 2017).
Alekh Agarwal, Haipeng Luo, Behnam Neyshabur and Robert E. Schapire.
Corralling a Band of Bandit Algorithms. [pdf]
In Proceedings of the 30th Conference on Learning Theory (COLT 2017).
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy and Robert E. Schapire.
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits. [proceedings site]
In Advances in Neural Information Processing Systems 29 (NIPS 2016).
Haipeng Luo, Alekh Agarwal, Nicolo Cesa-Bianchi and John Langford.
Efficient Second Order Online Learning via Sketching. [proceedings site]
In Advances in Neural Information Processing Systems 29 (NIPS 2016).
Elad Hazan and Haipeng Luo.
Variance-Reduced and Projection-Free Stochastic Optimization. [pdf] [supplementary]
In Proceedings of the 33rd International Conference on Machine Learning (ICML 2016).
Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo and Robert E. Schapire.
Fast Convergence of Regularized Learning in Games. [proceedings site] [talk] [slides] [poster]
In Advances in Neural Information Processing Systems 28 (NIPS 2015).   Best Paper Award
Alina Beygelzimer, Elad Hazan, Satyen Kale and Haipeng Luo.
Online Gradient Boosting. [proceedings site] [poster]
In Advances in Neural Information Processing Systems 28 (NIPS 2015).
Alina Beygelzimer, Satyen Kale and Haipeng Luo.
Optimal and Adaptive Algorithms for Online Boosting. [pdf] [supplementary] [slides] [poster]
In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015).   Best Paper Award
In Proceedings of the 25th International Joint Conference on Aritifical Intelligence (IJCAI 2016, sister conference best paper track) [short version]
Haipeng Luo and Robert E. Schapire.
Achieving All with No Parameters: AdaNormalHedge. [pdf] [short talk] [poster]
In Proceedings of the 28th Conference on Learning Theory (COLT 2015).
Haipeng Luo and Robert E. Schapire.
A Drifting-Games Analysis for Online Learning and Applications to Boosting. [proceedings site] [poster]
In Advances in Neural Information Processing Systems 27 (NIPS 2014).
Haipeng Luo, Patrick Haffner and Jean-Francois Paiement.
Accelerated Parallel Optimization Methods for Large Scale Machine Learning. [arXiv] [poster]
7th NIPS Workshop on Optimization for Machine Learning, 2014.
8th Annual Machine Learning Symposium, 2014. Google Spotlight Presentation Award.
Haipeng Luo and Robert E. Schapire.
Towards Minimax Online Learning with Unknown Time Horizon. [arXiv] [long talk] [short talk] [slides] [poster]
In Proceedings of the 31st International Conference on Machine Learning (ICML 2014).
Weijia Song, Zhen Xiao, Qi Chen and Haipeng Luo.
Adaptive Resource Provisioning for the Cloud Using Online Bin Packing. [pdf]
IEEE Transactions on Computers, 63:2647-2660, 2013.
Zhen Xiao, Qi Chen and Haipeng Luo.
Automatic Scaling of Internet Applications for Cloud Computing Services. [pdf]
IEEE Transactions on Computers, 63:1111-1123, 2012.