| LoRA: Low-rank adaptation of large language models EJ Hu, Y Shen, P Wallis, Z Allen-Zhu, Y Li, S Wang, L Wang, W Chen ICLR 2022: International Conference on Learning Representations, 2022 | 7566 | 2022 |
| A convergence theory for deep learning via over-parameterization Z Allen-Zhu, Y Li, Z Song ICML 2019: International Conference on Machine Learning, 2019 | 1601 | 2019 |
| Is Q-learning Provably Efficient? C Jin, Z Allen-Zhu, S Bubeck, MI Jordan NIPS 2018: Neural Information Processing Systems, 2018 | 967 | 2018 |
| Learning and generalization in overparameterized neural networks, going beyond two layers Z Allen-Zhu, Y Li, Y Liang NeurIPS 2019: Neural Information Processing Systems, 2019 | 868 | 2019 |
| Katyusha: the first direct acceleration of stochastic gradient methods Z Allen-Zhu STOC 2017: Symposium on Theory of Computing, 19-23, 2017 | 700 | 2017 |
| Variance reduction for faster non-convex optimization Z Allen-Zhu, E Hazan ICML 2016: International Conference on Machine Learning, 699-707, 2016 | 441 | 2016 |
| Towards understanding ensemble, knowledge distillation and self-distillation in deep learning Z Allen-Zhu, Y Li ICLR 2023: International Conference on Learning Representations, 2023 | 391 | 2023 |
| Linear coupling: An ultimate unification of gradient and mirror descent Z Allen-Zhu, L Orecchia ITCS 2017: Innovations in Theoretical Computer Science, 2017 | 388 | 2017 |
| Finding approximate local minima faster than gradient descent N Agarwal, Z Allen-Zhu, B Bullins, E Hazan, T Ma STOC 2017: Symposium on Theory of Computing, 1195-1199, 2017 | 354* | 2017 |
| Byzantine Stochastic Gradient Descent D Alistarh, Z Allen-Zhu, J Li NIPS 2018: Neural Information Processing Systems, 2018 | 340 | 2018 |
| A simple, combinatorial algorithm for solving SDD systems in nearly-linear time JA Kelner, L Orecchia, A Sidford, ZA Zhu STOC 2013: Symposium on Theory of Computing, 911-920, 2013 | 294 | 2013 |
| Natasha 2: Faster Non-Convex Optimization Than SGD Z Allen-Zhu NIPS 2018: Neural Information Processing Systems, 2018 | 263 | 2018 |
| Improved SVRG for non-strongly-convex or sum-of-non-convex objectives Z Allen-Zhu, Y Yuan ICML 2016: International Conference on Machine Learning, 1080-1089, 2016 | 237 | 2016 |
| What Can ResNet Learn Efficiently, Going Beyond Kernels? Z Allen-Zhu, Y Li NeurIPS 2019: Neural Information Processing Systems, 2019 | 222 | 2019 |
| Even faster accelerated coordinate descent using non-uniform sampling Z Allen-Zhu, Z Qu, P Richtárik, Y Yuan ICML 2016: International Conference on Machine Learning, 1110-1119, 2016 | 210 | 2016 |
| On the convergence rate of training recurrent neural networks Z Allen-Zhu, Y Li, Z Song NeurIPS 2019: Neural Information Processing Systems, 2019 | 204 | 2019 |
| Asymptotically optimal strategy-proof mechanisms for two-facility games P Lu, X Sun, Y Wang, ZA Zhu ACM-EC 2010: Conference on Economics and Computation, 315-324, 2010 | 201 | 2010 |
| Feature purification: How adversarial training performs robust deep learning Z Allen-Zhu, Y Li FOCS 2021: Symposium on Foundations of Computer Science, 977-988, 2022 | 165 | 2022 |
| Neon2: Finding Local Minima via First-Order Oracles Z Allen-Zhu, Y Li NIPS 2018: Neural Information Processing Systems, 2018 | 160 | 2018 |
| LazySVD: Even faster SVD decomposition yet without agonizing pain Z Allen-Zhu, Y Li NIPS 2016: Neural Information Processing Systems, 974-982, 2016 | 143 | 2016 |
Yuanzhi LiAssistant Professor at CMUVerified email at andrew.cmu.edu
