| Information-theoretic metric learning JV Davis, B Kulis, P Jain, S Sra, IS Dhillon Proceedings of the 24th international conference on Machine learning, 209-216, 2007 | 2758 | 2007 |
| Clustering on the Unit Hypersphere using von Mises-Fisher Distributions. A Banerjee, IS Dhillon, J Ghosh, S Sra Journal of Machine Learning Research 6 (9), 2005 | 1322 | 2005 |
| Contrastive learning with hard negative samples J Robinson, CY Chuang, S Sra, S Jegelka ICLR 2021, 2021 | 1160 | 2021 |
| Optimization for machine learning S Sra, S Nowozin, SJ Wright MIT press, 2011 | 1135 | 2011 |
| Stochastic Variance Reduction for Nonconvex Optimization SJ Reddi, A Hefny, S Sra, B Póczós, A Smola International Conference on Machine Learning (ICML), 2016 | 774 | 2016 |
| Why gradient clipping accelerates training: A theoretical justification for adaptivity J Zhang, T He, S Sra, A Jadbabaie International Conference on Learning Representations (ICLR 2020), 2019 | 773 | 2019 |
| Generalized nonnegative matrix approximations with Bregman divergences S Sra, I Dhillon Advances in neural information processing systems 18, 2005 | 709 | 2005 |
| Why are adaptive methods good for attention models? J Zhang, SP Karimireddy, A Veit, S Kim, S Reddi, S Kumar, S Sra Advances in Neural Information Processing Systems 33, 15383-15393, 2020 | 479* | 2020 |
| Minimum sum-squared residue co-clustering of gene expression data H Cho, IS Dhillon, Y Guan, S Sra Proceedings of the 2004 SIAM international conference on data mining, 114-125, 2004 | 440 | 2004 |
| First-order methods for geodesically convex optimization H Zhang, S Sra Conference on Learning Theory (COLT), 2016 | 376 | 2016 |
| Efficient filter flow for space-variant multiframe blind deconvolution M Hirsch, S Sra, B Schölkopf, S Harmeling 2010 IEEE Computer Society Conference on Computer Vision and Pattern …, 2010 | 337 | 2010 |
| Riemannian SVRG: Fast stochastic optimization on Riemannian manifolds H Zhang, S J Reddi, S Sra Advances in Neural Information Processing Systems 29, 2016 | 330 | 2016 |
| Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization SJ Reddi, S Sra, B Poczos, A Smola Advances in Neural Information Processing Systems, 2016 | 283 | 2016 |
| Entropic metric alignment for correspondence problems J Solomon, G Peyré, VG Kim, S Sra ACM Transactions on Graphics (ToG) 35 (4), 1-13, 2016 | 261 | 2016 |
| Randomized nonlinear component analysis D Lopez-Paz, S Sra, A Smola, Z Ghahramani, B Schölkopf International conference on machine learning, 1359-1367, 2014 | 254 | 2014 |
| Transformers learn to implement preconditioned gradient descent for in-context learning K Ahn, X Cheng, H Daneshmand, S Sra Advances in Neural Information Processing Systems 36, 45614-45650, 2023 | 250 | 2023 |
| Sign and basis invariant networks for spectral graph representation learning D Lim, J Robinson, L Zhao, T Smidt, S Sra, H Maron, S Jegelka arXiv preprint arXiv:2202.13013, 2022 | 241 | 2022 |
| Geometric Mean Metric Learning PH Zadeh, R Hosseini, S Sra International Conference on Machine Learning (ICML), 2016 | 237 | 2016 |
| A short note on parameter approximation for von Mises-Fisher distributions: and a fast implementation of Is(x) S Sra Computational Statistics 27 (1), 177-190, 2012 | 232 | 2012 |
| On variance reduction in stochastic gradient descent and its asynchronous variants SJ Reddi, A Hefny, S Sra, B Poczos, AJ Smola Advances in neural information processing systems, 2647-2655, 2015 | 222 | 2015 |
Inderjit S. DhillonVP, Google Fellow at Google & Professor of Computer Science at UT Austin, Ex-VP at AmazonVerified email at cs.utexas.edu
