| Finding approximate local minima faster than gradient descent N Agarwal, Z Allen-Zhu, B Bullins, E Hazan, T Ma Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing …, 2017 | 358* | 2017 |
| Second-order stochastic optimization for machine learning in linear time N Agarwal, B Bullins, E Hazan Journal of Machine Learning Research 18 (116), 1-40, 2017 | 341* | 2017 |
| Is local SGD better than minibatch SGD? B Woodworth, KK Patel, S Stich, Z Dai, B Bullins, B Mcmahan, O Shamir, ... International Conference on Machine Learning, 10334-10343, 2020 | 292 | 2020 |
| Online control with adversarial disturbances N Agarwal, B Bullins, E Hazan, S Kakade, K Singh International Conference on Machine Learning, 111-119, 2019 | 260 | 2019 |
| Efficient full-matrix adaptive regularization N Agarwal, B Bullins, X Chen, E Hazan, K Singh, C Zhang, Y Zhang International Conference on Machine Learning, 102-110, 2019 | 85* | 2019 |
| Adaptive regularization with cubics on manifolds N Agarwal, N Boumal, B Bullins, C Cartis arXiv preprint arXiv:1806.00065, 2018 | 72 | 2018 |
| The min-max complexity of distributed stochastic convex optimization with intermittent communication BE Woodworth, B Bullins, O Shamir, N Srebro Conference on Learning Theory, 4386-4437, 2021 | 50 | 2021 |
| Higher-order methods for convex-concave min-max optimization and monotone variational inequalities B Bullins, KA Lai SIAM Journal on Optimization 32 (3), 2208-2229, 2022 | 35 | 2022 |
| Not-So-Random Features B Bullins, C Zhang, Y Zhang International Conference on Learning Representations, 2018 | 28 | 2018 |
| Highly smooth minimization of non-smooth problems B Bullins Conference on Learning Theory, 988-1030, 2020 | 27 | 2020 |
| Generalize across tasks: Efficient algorithms for linear representation learning B Bullins, E Hazan, A Kalai, R Livni algorithmic learning theory, 235-246, 2019 | 25 | 2019 |
| Fast minimization of structured convex quartics B Bullins arXiv preprint arXiv:1812.10349, 2018 | 22 | 2018 |
| Optimal methods for higher-order smooth monotone variational inequalities D Adil, B Bullins, A Jambulapati, S Sachdeva arXiv preprint arXiv:2205.06167, 2022 | 20* | 2022 |
| Spectral properties of modularity matrices M Bolla, B Bullins, S Chaturapruek, S Chen, K Friedl Linear Algebra and Its Applications 473, 359-376, 2015 | 19* | 2015 |
| Towards optimal communication complexity in distributed non-convex optimization KK Patel, L Wang, BE Woodworth, B Bullins, N Srebro Advances in Neural Information Processing Systems 35, 13316-13328, 2022 | 18 | 2022 |
| Almost-linear-time Weighted -norm Solvers in Slightly Dense Graphs via Sparsification D Adil, B Bullins, R Kyng, S Sachdeva arXiv preprint arXiv:2102.06977, 2021 | 18 | 2021 |
| The limits of learning with missing data B Bullins, E Hazan, T Koren Advances in Neural Information Processing Systems 29, 2016 | 16 | 2016 |
| A stochastic newton algorithm for distributed convex optimization B Bullins, K Patel, O Shamir, N Srebro, BE Woodworth Advances in Neural Information Processing Systems 34, 26818-26830, 2021 | 15 | 2021 |
| Higher-order accelerated methods for faster non-smooth optimization B Bullins, R Peng arXiv preprint arXiv:1906.01621, 2019 | 15 | 2019 |
| Unifying width-reduced methods for quasi-self-concordant optimization D Adil, B Bullins, S Sachdeva Advances in Neural Information Processing Systems 34, 19122-19133, 2021 | 8 | 2021 |
Naman AgarwalSenior Research Scientist, Google AI PrincetonVerified email at google.com
