| Revisiting the nystrom method for improved large-scale machine learning A Gittens, M Mahoney International Conference on Machine Learning, 567-575, 2013 | 497 | 2013 |
| Improved matrix algorithms via the subsampled randomized Hadamard transform C Boutsidis, A Gittens SIAM Journal on Matrix Analysis and Applications 34 (3), 1301-1340, 2013 | 158 | 2013 |
| Scalable kernel k-means clustering with nystrom approximation: Relative-error bounds S Wang, A Gittens, MW Mahoney Journal of Machine Learning Research 20 (12), 1-49, 2019 | 143 | 2019 |
| Skip-gram− zipf+ uniform= vector additivity A Gittens, D Achlioptas, MW Mahoney Proceedings of the 55th Annual Meeting of the Association for Computational …, 2017 | 125 | 2017 |
| Sketched ridge regression: Optimization perspective, statistical perspective, and model averaging S Wang, A Gittens, MW Mahoney Journal of Machine Learning Research 18 (218), 1-50, 2018 | 101 | 2018 |
| Compact random feature maps R Hamid, Y Xiao, A Gittens, D DeCoste International conference on machine learning, 19-27, 2014 | 90 | 2014 |
| Matrix factorizations at scale: A comparison of scientific data analytics in Spark and C+ MPI using three case studies A Gittens, A Devarakonda, E Racah, M Ringenburg, L Gerhardt, ... 2016 IEEE International Conference on Big Data (Big Data), 204-213, 2016 | 86 | 2016 |
| The spectral norm error of the naive nystrom extension A Gittens arXiv preprint arXiv:1110.5305, 2011 | 82 | 2011 |
| Spectral clustering via the power method-provably C Boutsidis, P Kambadur, A Gittens International conference on machine learning, 40-48, 2015 | 77 | 2015 |
| The masked sample covariance estimator: an analysis using matrix concentration inequalities RY Chen, A Gittens, JA Tropp Information and Inference: A Journal of the IMA 1 (1), 2-20, 2012 | 74 | 2012 |
| Tail bounds for all eigenvalues of a sum of random matrices A Gittens, JA Tropp arXiv preprint arXiv:1104.4513, 2011 | 64 | 2011 |
| Malont: An ontology for malware threat intelligence N Rastogi, S Dutta, MJ Zaki, A Gittens, C Aggarwal International workshop on deployable machine learning for security defense …, 2020 | 57 | 2020 |
| Breaking locality accelerates block Gauss-Seidel S Tu, S Venkataraman, AC Wilson, A Gittens, MI Jordan, B Recht International Conference on Machine Learning, 3482-3491, 2017 | 37 | 2017 |
| Group collaborative representation for image set classification B Liu, L Jing, J Li, J Yu, A Gittens, MW Mahoney International Journal of Computer Vision 127, 181-206, 2019 | 35 | 2019 |
| H5spark: bridging the i/o gap between spark and scientific data formats on hpc systems J Liu, E Racah, Q Koziol, RS Canon, A Gittens, L Gerhardt, S Byna, ... Cray user group, 2016 | 34 | 2016 |
| Error bounds for random matrix approximation schemes A Gittens, JA Tropp arXiv preprint arXiv:0911.4108, 2009 | 34 | 2009 |
| Approximate spectral clustering via randomized sketching A Gittens, P Kambadur, C Boutsidis arXiv preprint arXiv:1311.2854, 2013 | 26 | 2013 |
| Prabhat Y Liu, E Racah, Q Koziol, RS Canon, A Gittens, L Gerhardt, S Byna, ... Correa, J, 2017 | 23 | 2017 |
| Synthesis, structure and characterization of two new antimony oxides–LaSb 3 O 9 and LaSb 5 O 12: Formation of LaSb 5 O 12 from the reaction of LaSb 3 O 9 with Sb 2 O 3 KM Ok, A Gittens, L Zhang, PS Halasyamani Journal of Materials Chemistry 14 (1), 116-120, 2004 | 22 | 2004 |
| Topics in randomized numerical linear algebra A Gittens California Institute of Technology, 2013 | 21 | 2013 |
Michael MahoneyProfessor of Statistics, UC BerkeleyVerified email at stat.berkeley.edu
