Artigos com autorizações de acesso público - Yuanzhi LiSaiba mais
Disponíveis em algum local: 39
Learning overparameterized neural networks via stochastic gradient descent on structured data
Y Li, Y Liang
Advances in neural information processing systems 31, 2018
Autorizações: US National Science Foundation, US Department of Defense
A latent variable model approach to pmi-based word embeddings
S Arora, Y Li, Y Liang, T Ma, A Risteski
Transactions of the Association for Computational Linguistics 4, 385-399, 2016
Autorizações: US National Science Foundation
Algorithmic regularization in over-parameterized matrix sensing and neural networks with quadratic activations
Y Li, T Ma, H Zhang
Conference On Learning Theory, 2-47, 2018
Autorizações: US National Science Foundation
Towards explaining the regularization effect of initial large learning rate in training neural networks
Y Li, C Wei, T Ma
Advances in neural information processing systems 32, 2019
Autorizações: US National Science Foundation
Linear algebraic structure of word senses, with applications to polysemy
S Arora, Y Li, Y Liang, T Ma, A Risteski
Transactions of the Association for Computational Linguistics 6, 483-495, 2018
Autorizações: US National Science Foundation, US Department of Defense
Gradient descent on neural networks typically occurs at the edge of stability
JM Cohen, S Kaur, Y Li, JZ Kolter, A Talwalkar
arXiv preprint arXiv:2103.00065, 2021
Autorizações: US National Science Foundation, US Department of Defense
LazySVD: Even faster SVD decomposition yet without agonizing pain
Z Allen-Zhu, Y Li
Advances in neural information processing systems 29, 2016
Autorizações: US National Science Foundation
Towards understanding the mixture-of-experts layer in deep learning
Z Chen, Y Deng, Y Wu, Q Gu, Y Li
Advances in neural information processing systems 35, 23049-23062, 2022
Autorizações: US National Science Foundation
Much faster algorithms for matrix scaling
Z Allen-Zhu, Y Li, R Oliveira, A Wigderson
2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS …, 2017
Autorizações: US National Science Foundation
The probability flow ode is provably fast
S Chen, S Chewi, H Lee, Y Li, J Lu, A Salim
Advances in Neural Information Processing Systems 36, 68552-68575, 2023
Autorizações: US National Science Foundation
Operator scaling via geodesically convex optimization, invariant theory and polynomial identity testing
Z Allen-Zhu, A Garg, Y Li, R Oliveira, A Wigderson
Proceedings of the 50th annual ACM SIGACT symposium on theory of computing …, 2018
Autorizações: US National Science Foundation
Near-optimal method for highly smooth convex optimization
S Bubeck, Q Jiang, YT Lee, Y Li, A Sidford
Conference on Learning Theory, 492-507, 2019
Autorizações: US National Science Foundation
Near Optimal Methods for Minimizing Convex Functions with Lipschitz -th Derivatives
A Gasnikov, P Dvurechensky, E Gorbunov, E Vorontsova, ...
Conference on Learning Theory, 1392-1393, 2019
Autorizações: US National Science Foundation, National Natural Science Foundation of China
How do transformers learn topic structure: Towards a mechanistic understanding
Y Li, Y Li, A Risteski
International Conference on Machine Learning, 19689-19729, 2023
Autorizações: US National Science Foundation
Near-optimal discrete optimization for experimental design: A regret minimization approach
Z Allen-Zhu, Y Li, A Singh, Y Wang
Mathematical Programming 186, 439-478, 2021
Autorizações: US National Science Foundation, US Department of Defense
{PET}: Optimizing tensor programs with partially equivalent transformations and automated corrections
H Wang, J Zhai, M Gao, Z Ma, S Tang, L Zheng, Y Li, K Rong, Y Chen, ...
15th USENIX Symposium on Operating Systems Design and Implementation (OSDI …, 2021
Autorizações: National Natural Science Foundation of China
Complexity of highly parallel non-smooth convex optimization
S Bubeck, Q Jiang, YT Lee, Y Li, A Sidford
Advances in neural information processing systems 32, 2019
Autorizações: US National Science Foundation
Near-optimal design of experiments via regret minimization
Z Allen-Zhu, Y Li, A Singh, Y Wang
International Conference on Machine Learning, 126-135, 2017
Autorizações: US National Science Foundation
Linear convergence of a frank-wolfe type algorithm over trace-norm balls
Z Allen-Zhu, E Hazan, W Hu, Y Li
Advances in neural information processing systems 30, 2017
Autorizações: US National Science Foundation
Chasing nested convex bodies nearly optimally
S Bubeck, B Klartag, YT Lee, Y Li, M Sellke
Proceedings of the Fourteenth Annual ACM-SIAM Symposium on Discrete …, 2020
Autorizações: US National Science Foundation
As informações de publicação e financiamento são determinadas automaticamente por um programa informático.