| Don't use large mini-batches, use local SGD T Lin, SU Stich, KK Patel, M Jaggi arXiv preprint arXiv:1808.07217, 2018 | 557 | 2018 |
| 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 | 347 | 2020 |
| Minibatch vs local sgd for heterogeneous distributed learning BE Woodworth, KK Patel, N Srebro Advances in Neural Information Processing Systems 33, 6281-6292, 2020 | 294 | 2020 |
| Communication trade-offs for local-sgd with large step size KK Patel, A Dieuleveut Advances In Neural Information Processing Systems 32 (32), 2825-2830, 2019 | 93* | 2019 |
| Corruption-tolerant bandit learning S Kapoor, KK Patel, P Kar Machine Learning 108 (4), 687-715, 2019 | 72 | 2019 |
| Towards Optimal Communication Complexity in Distributed Non-Convex Optimization KK Patel, L Wang, B Woodworth, B Bullins, N Srebro Advances in Neural Information Systems 36, 2022 | 31 | 2022 |
| The limits and potentials of local sgd for distributed heterogeneous learning with intermittent communication KK Patel, M Glasgow, A Zindari, L Wang, SU Stich, Z Cheng, N Joshi, ... The Thirty Seventh Annual Conference on Learning Theory, 4115-4157, 2024 | 30* | 2024 |
| On Convexity and Linear Mode Connectivity in Neural Networks D Yunis, KK Patel, PHP Savarese, G Vardi, J Frankle, M Walter, K Livescu, ... OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop), 2022 | 29 | 2022 |
| Federated online and bandit convex optimization KK Patel, L Wang, A Saha, N Srebro International Conference on Machine Learning, 27439-27460, 2023 | 28* | 2023 |
| 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 | 23 | 2021 |
| Approaching deep learning through the spectral dynamics of weights D Yunis, KK Patel, S Wheeler, P Savarese, G Vardi, K Livescu, M Maire, ... arXiv preprint arXiv:2408.11804, 2024 | 12* | 2024 |
| Online combinatorial optimization with group fairness constraints N Golrezaei, R Niazadeh, KK Patel, F Susan MIT Sloan Research Paper, 2024 | 8 | 2024 |
| On the effect of defections in federated learning and how to prevent them M Han, KK Patel, H Shao, L Wang arXiv preprint arXiv:2311.16459, 2023 | 8 | 2023 |
| Personalized Federated Training of Diffusion Models with Privacy Guarantees KK Patel, W Zhang, L Wang arXiv preprint arXiv:2504.00952, 2025 | 2 | 2025 |
| Efficient private federated non-convex optimization with shuffled model L Wang, X Zhou, KK Patel, L Tang, A Saha Privacy Regulation and Protection in Machine Learning, 2024 | 2 | 2024 |
| Privacy-Enhancing Sequential Learning under Heterogeneous Selection Bias in Multi-Site EHR Data R Kundu, X Shi, KK Patel, L Ohno-Machado, M Salvatore, PXK Song, ... medRxiv, 2025.09. 26.25336642, 2025 | 1 | 2025 |
| The limitations of model retraining in the face of performativity A Kabra, KK Patel arXiv preprint arXiv:2408.08499, 2024 | 1 | 2024 |
| Distributionally Robust Linear Regression With Block Lewis Weights NS Manoj, KK Patel OPT 2024: Optimization for Machine Learning, 0 | 1 | |
| What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness KK Patel arXiv preprint arXiv:2507.00195, 2025 | | 2025 |
| Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity KK Patel, A Zindari, SU Stich, L Wang The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025 | | 2025 |
Nathan SrebroProfessor, TTIC and University of ChicagoVerified email at ttic.edu
