| How Powerful are Graph Neural Networks? K Xu, W Hu, J Leskovec, S Jegelka arXiv preprint arXiv:1810.00826, 2018 | 1075 | 2018 |
| Deep metric learning via lifted structured feature embedding H Oh Song, Y Xiang, S Jegelka, S Savarese Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2016 | 883 | 2016 |
| Representation learning on graphs with jumping knowledge networks K Xu, C Li, Y Tian, T Sonobe, K Kawarabayashi, S Jegelka International Conference on Machine Learning, 5453-5462, 2018 | 356 | 2018 |
| On learning to localize objects with minimal supervision HO Song, R Girshick, S Jegelka, J Mairal, Z Harchaoui, T Darrell International Conference on Machine Learning (ICML), 2014 | 247 | 2014 |
| Deep Metric Learning via Facility Location HO Song, S Jegelka, V Rathod, K Murphy CVPR, 2017 | 224 | 2017 |
| Submodularity beyond submodular energies: coupling edges in graph cuts S Jegelka, J Bilmes Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on …, 2011 | 210 | 2011 |
| Max-value entropy search for efficient Bayesian optimization Z Wang, S Jegelka Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017 | 163 | 2017 |
| Weakly-supervised discovery of visual pattern configurations HO Song, YJ Lee, S Jegelka, T Darrell Advances in neural information processing systems 27, 1637-1645, 2014 | 155 | 2014 |
| Fast semidifferential-based submodular function optimization R Iyer, S Jegelka, J Bilmes International Conference on Machine Learning (ICML), 2013 | 121 | 2013 |
| Curvature and optimal algorithms for learning and minimizing submodular functions RK Iyer, S Jegelka, JA Bilmes Advances in Neural Information Processing Systems 26, 2742-2750, 2013 | 96 | 2013 |
| Resnet with one-neuron hidden layers is a universal approximator H Lin, S Jegelka Advances in neural information processing systems 31, 6169-6178, 2018 | 93 | 2018 |
| A principled deep random field model for image segmentation P Kohli, A Osokin, S Jegelka Proceedings of the IEEE conference on computer vision and pattern …, 2013 | 89 | 2013 |
| Reflection methods for user-friendly submodular optimization S Jegelka, F Bach, S Sra Advances in Neural Information Processing Systems 26, 1313-1321, 2013 | 80 | 2013 |
| Fast kernel-based independent component analysis H Shen, S Jegelka, A Gretton IEEE transactions on signal processing 57 (9), 3498-3511, 2009 | 77 | 2009 |
| Virtual screening of inorganic materials synthesis parameters with deep learning E Kim, K Huang, S Jegelka, E Olivetti npj Computational Materials 3 (53), 2017 | 75 | 2017 |
| Optimization as Estimation with Gaussian Processes in Bandit Settings Z Wang, B Zhou, S Jegelka Artificial Intelligence and Statistics (AISTATS), 2016 | 73 | 2016 |
| On fast approximate submodular minimization S Jegelka, H Lin, JA Bilmes Advances in Neural Information Processing Systems 24, 460-468, 2011 | 67 | 2011 |
| Parallel streaming Wasserstein barycenters M Staib, S Claici, JM Solomon, S Jegelka Advances in Neural Information Processing Systems 30, 2647-2658, 2017 | 62 | 2017 |
| Submodular meets structured: Finding diverse subsets in exponentially-large structured item sets A Prasad, S Jegelka, D Batra Advances in Neural Information Processing Systems 27, 2645-2653, 2014 | 61 | 2014 |
| Fast DPP sampling for Nyström with application to kernel methods C Li, S Jegelka, S Sra Proceedings of the 33rd International Conference on International Conference …, 2016 | 59 | 2016 |
Suvrit SraMITVerified email at mit.edu
