# Ofer Dekel’s Publications

*Sparse Multi-Prototype Classification.* Vikas Garg, Lin Xiao, and Ofer Dekel. To appear in Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2018. `Bu`

*Online Learning with a Hint.* Ofer Dekel, Arthur Flajolet, Nika Haghtalab, and Patrick Jaillet. Advances in Neural Information Processing Systems 30, 2017. `OL`

*Adaptive Neural Networks for Efficient Inference.* Tolga Bolukbasi, Joseph Wang, Ofer Dekel, and Venkatesh Saligrama. Proceedings of the Thirty Forth International Conference on Machine Learning, 2017. `Bu`

*Linear Learning with Sparse Data.* Ofer Dekel. Technical Report, 2016. `AE`

*Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff.* Ofer Dekel, Ronen Eldan, and Tomer Koren. Advances in Neural Information Processing Systems 28, 2015. `Ba`

*Bandit Convex Optimization: sqrt(T) Regret in One Dimension.* Sebastien Bubeck, Ofer Dekel, Tomer Koren, and Yuval Peres. Proceedings of the 28th Annual Conference on Learning Theory, 2015. `Ba`

*Online Learning with Feedback Graphs: Beyond Bandits.* Noga Alon, Nicolo Cesa-Bianchi, Ofer Dekel, and Tomer Koren. Proceedings of the 28th Annual Conference on Learning Theory, 2015. `Ba`

*The Blinded Bandit: Learning with Adaptive Feedback.* Ofer Dekel, Elad Hazan, and Tomer Koren. Advances in Neural Information Processing Systems 27, 2014. `Ba`

*Online Learning with Composite Loss Functions.* Ofer Dekel, Jian Ding, Tomer Koren, and Yuval Peres. Proceedings of the 27th Annual Conference on Learning Theory, 2014. `AA`

`Ba`

`OL`

*Bandits with Switching Costs: T^(2/3) Regret.* Ofer Dekel, Jian Ding, Tomer Koren, and Yuval Peres. Proceedings of the 46th Annual Symposium on the Theory of Computing, 2014. `Ba`

`LB`

*Online Learning with Switching Costs and Other Adaptive Adversaries.* Nicolo Cesa-Bianchi, Ofer Dekel, and Ohad Shamir. Advances in Neural Information Processing Systems 26, pages 1160-1168, 2013. `AA`

`Ba`

`LB`

`OL`

*Better Rates for Any Adversarial Deterministic MDP.* Ofer Dekel and Elad Hazan. Proceedings of the Thirtieth International Conference on Machine Learning, 2013. `AA`

`Ba`

`MP`

*Selective Sampling and Active Learning from Single and Multiple Teachers.* Ofer Dekel, Claudio Gentile, and Karthik Sridharan. Journal of Machine Learning Research, 13:2655-2697, 2012. `AL`

`MT`

*Optimal Distributed Online Prediction using Mini-Batches.* Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, and Lin Xiao. Journal of Machine Learning Research, 13:165-202, 2012. `DL`

`OL`

*Deterministic MDPs with Adversarial Rewards and Bandit Feedback.* Raman Arora, Ofer Dekel, and Ambuj Tewari. Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, 2012. `AA`

`Ba`

`MP`

*Online Bandit Learning Against an Adaptive Adversary: from Regret to Policy Regret.* Raman Arora, Ofer Dekel, and Ambuj Tewari. Proceedings of the Twenty-Ninth International Conference on Machine Learning, 2012. `AA`

`Ba`

*There’s a Hole in My Dataspace: Piecewise Predictors for Heterogeneous Learning Problems.* Ofer Dekel and Ohad Shamir. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings 22, 2012. `EM`

*Optimal Distributed Online Prediction.* Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, and Lin Xiao. Proceedings of the Twenty-Eighth International Conference on Machine Learning, 2011. `DL`

`OL`

*Bundle Selling by Online Estimation of Valuation Functions.* Daniel Vainsencher, Ofer Dekel, and Shie Mannor. Proceedings of the Twenty-Eighth International Conference on Machine Learning, 2011. `OL`

*Incentive Compatible Regression Learning.* Ofer Dekel, Felix Fischer, and Ariel D. Procaccia. Journal of Computer and System Sciences, 76:759-777, 2010. `MD`

`LT`

*Learning to Classify with Missing and Corrupted Features.* Ofer Dekel, Ohad Shamir, and Lin Xiao. Machine Learning Journal, 81:149-178, 2010.

*Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback.* Alekh Agarwal, Ofer Dekel, and Lin Xiao. Proceedings of the Twenty-Third Annual Conference on Learning Theory, pages 28-40, 2010. `Ba`

*Robust Selective Sampling from Single and Multiple Teachers.* Ofer Dekel, Claudio Gentile, and Karthik Sridharan. Proceedings of the Twenty-Third Annual Conference on Learning Theory, pages 346-358, 2010. `AL`

`MT`

*Multiclass-Multilabel Classification with More Classes than Examples.* Ofer Dekel and Ohad Shamir. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR 9:137-144, 2010. `Ex`

*Distribution-Calibrated Hierarchical Classification.* Ofer Dekel. Advances in Neural Information Processing Systems 22, 2010. `Ex`

*Individual Sequence Prediction using Memory-Efficient Context Trees.* Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. IEEE Transactions on Information Theory, 55(11):5251-5262, 2009. `OL`

*Vox Populi: Collecting High-Quality Labels from a Crowd.* Ofer Dekel and Ohad Shamir. Proceedings of the Twenty-Second Annual Conference on Learning Theory, 2009. `MT`

*Good Learners for Evil Teachers.* Ofer Dekel and Ohad Shamir. Proceedings of the Twenty-Sixth International Conference on Machine Learning, pages 216-223, 2009. `MT`

*From Online to Batch Learning with Cutoff Averaging.* Ofer Dekel. Advances in Neural Information Processing Systems 21, 2009. `LT`

*The Forgetron: A Kernel-Based Perceptron on a Budget.* Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. SIAM Journal on Computing, 37(5):1342-1372, 2008. `Bu`

`OL`

`SV`

*Learning to Classify with Missing and Corrupted features.* Ofer Dekel and Ohad Shamir. Proceedings of the Twenty-Fifth International Conference on Machine Learning, 2008.

*Incentive Compatible Regression Learning.* Ofer Dekel, Felix Fischer, and Ariel Procaccia. Proceedings of the Nineteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pages 884-893, 2008. `MD`

*Online Learning of Multiple Tasks with a Shared Loss.* Ofer Dekel, Philip M. Long, and Yoram Singer. Journal of Machine Learning Research, 8:2233-2264, 2007.

*A Boosting Algorithm for Label Covering in Multilabel Problems.* Yonatan Amit, Ofer Dekel, and Yoram Singer. Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007. `EM`

*Support Vector Machines on a Budget.* Ofer Dekel and Yoram Singer. Advances in Neural Information Processing Systems 19, pages 345-352. MIT Press, 2007. `Bu`

`SV`

*Online Passive-Aggressive Algorithms.* Koby Crammer, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz, and Yoram Singer. Journal of Machine Learning Research, 7:551-585, 2006. `OL`

*Online Multitask Learning.* Ofer Dekel, Philip M. Long, and Yoram Singer. Proceedings of the Nineteenth Annual Conference on Learning Theory, pages 453-467. Springer LNAI 4005, 2006. `OL`

*Data-Driven Online to Batch Conversions.* Ofer Dekel and Yoram Singer. Advances in Neural Information Processing Systems 18, pages 267-274. MIT Press, 2006. `LT`

*The Forgetron: A Kernel-Based Perceptron on a Fixed Budget.* Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. Advances in Neural Information Processing Systems 18, pages 259-266. MIT Press, 2006. `Bu`

`OL`

`SV`

*Smooth Epsilon-Insensitive Regression by Loss Symmetrization.* Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. Journal of Machine Learning Research, 6:711-741, 2005.

*The Power of Selective Memory: Self-Bounded Learning of Prediction Suffix Trees.* Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. Advances in Neural Information Processing Systems 17, pages 345-352. MIT Press, 2005. `OL`

*An Online Algorithm for Hierarchical Phoneme Classification.* Ofer Dekel, Joseph Keshet, and Yoram Singer. Machine Learning for Multimodal Interaction: First International Workshop, pages 146-158. Springer LNAI 3361, 2005. `OL`

*Large Margin Hierarchical Classification.* Ofer Dekel, Joseph Keshet, and Yoram Singer. Proceedings of the Twenty-First International Conference on Machine Learning, 2004.

*Log-Linear Models for Label Ranking.* Ofer Dekel, Christopher Manning, and Yoram Singer. Advances in Neural Information Processing Systems 16, 2004.

*Online Passive-Aggressive Algorithms.* Koby Crammer, Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. Advances in Neural Information Processing Systems 16. MIT Press, 2004. `OL`

*Smooth Epsilon-Insensitive Regression by Loss Symmetrization.* Ofer Dekel, Shai Shalev-Shwartz, and Yoram Singer. Proceedings of the Sixteenth Annual Conference on Computational Learning Theory, pages 433-447. Springer LNAI 2777, 2003.

*Multiclass Categorization by Probabilistic Embeddings.* Ofer Dekel and Yoram Singer. Advances in Neural Information Processing Systems 15, pages 945-952. MIT Press, 2003.

### Tag Legend

`AA` Adaptive adversaries in online learning |

`AE` Algorithm engineering and efficient implementation |

`AL` Active learning |

`Ba` Bandits |

`Bu` Learning on a budget |

`DL` Distrubuted learning |

`Ex` Extreme classification (classification with many labels) |

`EM` Boosting and ensemble methods |

`LB` Lower bounds |

`LT` Statistical learning theory |

`MD` Mechanism design and incentives in machine learning |

`MP` Markov decision processes |

`MT` Learning from multiple teachers and crowdsourcing |

`OL` Online learning |

`SV` Support vector machines and kernel methods |