Implicit regularization in matrix factorization S Gunasekar, BE Woodworth, S Bhojanapalli, B Neyshabur, N Srebro Advances in neural information processing systems 30, 2017 | 518 | 2017 |
Learning non-discriminatory predictors B Woodworth, S Gunasekar, MI Ohannessian, N Srebro Conference on Learning Theory, 1920-1953, 2017 | 431 | 2017 |
Kernel and rich regimes in overparametrized models B Woodworth, S Gunasekar, JD Lee, E Moroshko, P Savarese, I Golan, ... Conference on Learning Theory, 3635-3673, 2020 | 355 | 2020 |
A field guide to federated optimization J Wang, Z Charles, Z Xu, G Joshi, HB McMahan, M Al-Shedivat, G Andrew, ... arXiv preprint arXiv:2107.06917, 2021 | 332 | 2021 |
Lower bounds for non-convex stochastic optimization Y Arjevani, Y Carmon, JC Duchi, DJ Foster, N Srebro, B Woodworth Mathematical Programming 199 (1), 165-214, 2023 | 314 | 2023 |
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 | 270 | 2020 |
Tight complexity bounds for optimizing composite objectives BE Woodworth, N Srebro Advances in neural information processing systems 29, 2016 | 221 | 2016 |
Minibatch vs local sgd for heterogeneous distributed learning BE Woodworth, KK Patel, N Srebro Advances in Neural Information Processing Systems 33, 6281-6292, 2020 | 201 | 2020 |
Graph oracle models, lower bounds, and gaps for parallel stochastic optimization BE Woodworth, J Wang, A Smith, B McMahan, N Srebro Advances in neural information processing systems 31, 2018 | 128 | 2018 |
Training well-generalizing classifiers for fairness metrics and other data-dependent constraints A Cotter, M Gupta, H Jiang, N Srebro, K Sridharan, S Wang, B Woodworth, ... International Conference on Machine Learning, 1397-1405, 2019 | 113 | 2019 |
Implicit bias in deep linear classification: Initialization scale vs training accuracy E Moroshko, BE Woodworth, S Gunasekar, JD Lee, N Srebro, D Soudry Advances in neural information processing systems 33, 22182-22193, 2020 | 86 | 2020 |
On the implicit bias of initialization shape: Beyond infinitesimal mirror descent S Azulay, E Moroshko, MS Nacson, BE Woodworth, N Srebro, ... International Conference on Machine Learning, 468-477, 2021 | 71 | 2021 |
The complexity of making the gradient small in stochastic convex optimization DJ Foster, A Sekhari, O Shamir, N Srebro, K Sridharan, B Woodworth Conference on Learning Theory, 1319-1345, 2019 | 54 | 2019 |
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 | 45 | 2021 |
Asynchronous SGD beats minibatch SGD under arbitrary delays K Mishchenko, F Bach, M Even, BE Woodworth Advances in Neural Information Processing Systems 35, 420-433, 2022 | 43 | 2022 |
Lower bound for randomized first order convex optimization B Woodworth, N Srebro arXiv preprint arXiv:1709.03594, 2017 | 38 | 2017 |
The gradient complexity of linear regression M Braverman, E Hazan, M Simchowitz, B Woodworth Conference on Learning Theory, 627-647, 2020 | 35 | 2020 |
Mirrorless mirror descent: A natural derivation of mirror descent S Gunasekar, B Woodworth, N Srebro International Conference on Artificial Intelligence and Statistics, 2305-2313, 2021 | 34 | 2021 |
An even more optimal stochastic optimization algorithm: minibatching and interpolation learning BE Woodworth, N Srebro Advances in Neural Information Processing Systems 34, 7333-7345, 2021 | 25 | 2021 |
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 |