| Metric learning by collapsing classes A Globerson, S Roweis Advances in neural information processing systems 18, 451-458, 2005 | 840 | 2005 |
| Fixing max-product: Convergent message passing algorithms for MAP LP-relaxations A Globerson, T Jaakkola Advances in neural information processing systems 20, 553-560, 2007 | 407 | 2007 |
| Nightmare at test time: robust learning by feature deletion A Globerson, S Roweis Proceedings of the 23rd international conference on Machine learning, 353-360, 2006 | 383 | 2006 |
| Tightening LP relaxations for MAP using message passing D Sontag, T Meltzer, A Globerson, TS Jaakkola, Y Weiss arXiv preprint arXiv:1206.3288, 2012 | 353 | 2012 |
| Euclidean embedding of co-occurrence data A Globerson, G Chechik, F Pereira, N Tishby | 265 | 2007 |
| Globally optimal gradient descent for a convnet with gaussian inputs A Brutzkus, A Globerson International conference on machine learning, 605-614, 2017 | 257 | 2017 |
| Learning Bayesian network structure using LP relaxations T Jaakkola, D Sontag, A Globerson, M Meila Proceedings of the Thirteenth International Conference on Artificial …, 2010 | 252 | 2010 |
| Introduction to dual composition for inference D Sontag, A Globerson, T Jaakkola Optimization for Machine Learning, 2011 | 244 | 2011 |
| Information Bottleneck for Gaussian Variables. G Chechik, A Globerson, N Tishby, Y Weiss, P Dayan Journal of machine learning research 6 (1), 2005 | 239 | 2005 |
| Exponentiated gradient algorithms for conditional random fields and max-margin markov networks M Collins, A Globerson, T Koo, X Carreras Pérez, P Bartlett Journal of Machine Learning Research 9, 1775-1822, 2008 | 202 | 2008 |
| SGD learns over-parameterized networks that provably generalize on linearly separable data A Brutzkus, A Globerson, E Malach, S Shalev-Shwartz arXiv preprint arXiv:1710.10174, 2017 | 185 | 2017 |
| Selective sharing for multilingual dependency parsing T Naseem, R Barzilay, A Globerson The Association for Computational Linguistics, 2012 | 141 | 2012 |
| Structured prediction models via the matrix-tree theorem T Koo, A Globerson, X Carreras Pérez, M Collins Joint Conference on Empirical Methods in Natural Language Processing and …, 2007 | 138 | 2007 |
| Convergent message passing algorithms-a unifying view T Meltzer, A Globerson, Y Weiss arXiv preprint arXiv:1205.2625, 2012 | 137 | 2012 |
| Sufficient dimensionality reduction A Globerson, N Tishby Journal of Machine Learning Research 3 (Mar), 1307-1331, 2003 | 133 | 2003 |
| Convex learning with invariances CH Teo, A Globerson, ST Roweis, AJ Smola Advances in neural information processing systems, 1489-1496, 2008 | 124 | 2008 |
| Cross-lingual alignment of contextual word embeddings, with applications to zero-shot dependency parsing T Schuster, O Ram, R Barzilay, A Globerson arXiv preprint arXiv:1902.09492, 2019 | 121 | 2019 |
| Collective entity resolution with multi-focal attention A Globerson, N Lazic, S Chakrabarti, A Subramanya, M Ringaard, ... | 101 | 2016 |
| Learning efficiently with approximate inference via dual losses O Meshi, D Sontag, T Jaakkola, A Globerson International Machine Learning Society, 2010 | 88 | 2010 |
| An LP View of the M-best MAP problem M Fromer, A Globerson Advances in Neural Information Processing Systems 22, 567-575, 2009 | 84 | 2009 |
Tommi JaakkolaMITcsail.mit.edu의 이메일 확인됨
