Stochastic gradient descent, weighted sampling, and the randomized kaczmarz algorithm D Needell, R Ward, N Srebro Advances in neural information processing systems 27, 1017-1025, 2014 | 717 | 2014 |
Phi-3 technical report: A highly capable language model locally on your phone M Abdin, J Aneja, H Awadalla, A Awadallah, AA Awan, N Bach, A Bahree, ... arXiv preprint arXiv:2404.14219, 2024 | 509 | 2024 |
Adagrad stepsizes: Sharp convergence over nonconvex landscapes R Ward, X Wu, L Bottou Journal of Machine Learning Research 21 (219), 1-30, 2020 | 444* | 2020 |
New and improved Johnson–Lindenstrauss embeddings via the restricted isometry property F Krahmer, R Ward SIAM Journal on Mathematical Analysis 43 (3), 1269-1281, 2011 | 338 | 2011 |
Low-rank matrix recovery via iteratively reweighted least squares minimization M Fornasier, H Rauhut, R Ward SIAM Journal on Optimization 21 (4), 1614-1640, 2011 | 280 | 2011 |
Stable image reconstruction using total variation minimization D Needell, R Ward SIAM Journal on Imaging Sciences 6 (2), 1035-1058, 2013 | 258 | 2013 |
Sparse Legendre expansions via ℓ1-minimization H Rauhut, R Ward Journal of approximation theory 164 (5), 517-533, 2012 | 255 | 2012 |
Stable and robust sampling strategies for compressive imaging F Krahmer, R Ward IEEE transactions on image processing 23 (2), 612-622, 2013 | 228* | 2013 |
Exact recovery of chaotic systems from highly corrupted data G Tran, R Ward Multiscale Modeling & Simulation 15 (3), 1108-1129, 2017 | 199 | 2017 |
One-bit compressive sensing with norm estimation K Knudson, R Saab, R Ward IEEE Transactions on Information Theory 62 (5), 2748-2758, 2016 | 196 | 2016 |
Extracting sparse high-dimensional dynamics from limited data H Schaeffer, G Tran, R Ward SIAM Journal on Applied Mathematics 78 (6), 3279-3295, 2018 | 190 | 2018 |
Compressed sensing with cross validation R Ward IEEE Transactions on Information Theory 55 (12), 5773-5782, 2009 | 186 | 2009 |
Interpolation via weighted ℓ1 minimization H Rauhut, R Ward Applied and Computational Harmonic Analysis 40 (2), 321-351, 2016 | 177 | 2016 |
Phi-2: The surprising power of small language models M Javaheripi, S Bubeck, M Abdin, J Aneja, S Bubeck, CCT Mendes, ... Microsoft Research Blog 1 (3), 3, 2023 | 165 | 2023 |
Coherent matrix completion Y Chen, S Bhojanapalli, S Sanghavi, R Ward International Conference on Machine Learning, 674-682, 2014 | 151 | 2014 |
Relax, no need to round: Integrality of clustering formulations P Awasthi, AS Bandeira, M Charikar, R Krishnaswamy, S Villar, R Ward Proceedings of the 2015 Conference on Innovations in Theoretical Computer …, 2015 | 135 | 2015 |
Completing any low-rank matrix, provably Y Chen, S Bhojanapalli, S Sanghavi, R Ward The Journal of Machine Learning Research 16 (1), 2999-3034, 2015 | 123 | 2015 |
Clustering subgaussian mixtures by semidefinite programming DG Mixon, S Villar, R Ward arXiv preprint arXiv:1602.06612, 2016 | 120 | 2016 |
Near-optimal compressed sensing guarantees for total variation minimization D Needell, R Ward IEEE transactions on image processing 22 (10), 3941-3949, 2013 | 95 | 2013 |
Wngrad: Learn the learning rate in gradient descent X Wu, R Ward, L Bottou arXiv preprint arXiv:1803.02865, 2018 | 94 | 2018 |