A fast optimization view: Reformulating single layer attention in llm based on tensor and svm trick, and solving it in matrix multiplication time Y Gao, Z Song, W Wang, J Yin
arXiv preprint arXiv:2309.07418, 2023
39 2023 An iterative algorithm for rescaled hyperbolic functions regression Y Gao, Z Song, J Yin
The 28th International Conference on Artificial Intelligence and Statistics …, 2025
33 2025 Gradientcoin: A peer-to-peer decentralized large language models Y Gao, Z Song, J Yin
arXiv preprint arXiv:2308.10502, 2023
25 2023 Conv-basis: A new paradigm for efficient attention inference and gradient computation in transformers Y Liang, H Liu, Z Shi, Z Song, Z Xu, J Yin
arXiv preprint arXiv:2405.05219, 2024
24 2024 Low rank matrix completion via robust alternating minimization in nearly linear time Y Gu, Z Song, J Yin, L Zhang
The Twelfth International Conference on Learning Representations (ICLR 2024), 2024
23 2024 Solving attention kernel regression problem via pre-conditioner Z Song, J Yin, L Zhang
The 27th International Conference on Artificial Intelligence and Statistics …, 2024
14 2024 A unified scheme of resnet and softmax Z Song, W Wang, J Yin
arXiv preprint arXiv:2309.13482, 2023
12 2023 A Nearly-Optimal Bound for Fast Regression with Z Song, M Ye, J Yin, L Zhang
International Conference on Machine Learning, 32463-32482, 2023
9 2023 Dynamical fractal: Theory and case study J Yin
Chaos, Solitons & Fractals 176, 114190, 2023
8 2023 Federated Empirical Risk Minimization via Second-Order Method S Bian, Z Song, J Yin
arXiv preprint arXiv:2305.17482, 2023
8 2023 Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression Z Li, Z Song, Z Wang, J Yin
arXiv preprint arXiv:2311.15390, 2023
7 2023 Efficient alternating minimization with applications to weighted low rank approximation Z Song, M Ye, J Yin, L Zhang
The Twelfth International Conference on Learning Representations (ICLR 2025), 2025
6 2025 InstaHide's Sample Complexity When Mixing Two Private Images B Huang, Z Song, R Tao, J Yin, R Zhang, D Zhuo
arXiv preprint arXiv:2011.11877, 2020
5 2020 Faster robust tensor power method for arbitrary order Y Deng, Z Song, J Yin
arXiv preprint arXiv:2306.00406, 2023
4 2023 Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters Z Song, J Yin, R Zhang
The 28th Annual Quantum Information Processing Conference (QIP 2025), 2025
3 2025 The Expressibility of Polynomial based Attention Scheme Z Song, G Xu, J Yin
arXiv preprint arXiv:2310.20051, 2023
3 2023 A Faster J Liang, S Sarkhel, Z Song, C Yin, J Yin, D Zhuo
arXiv preprint arXiv:2211.15118, 2022
3 2022 A Dynamic Low-Rank Fast Gaussian Transform B Huang, Z Song, O Weinstein, J Yin, H Zhang, R Zhang
arXiv preprint arXiv:2202.12329, 2022
3 * 2022 Query complexity of active learning for function family with nearly orthogonal basis X Chen, Z Song, B Sun, J Yin, D Zhuo
arXiv preprint arXiv:2306.03356, 2023
2 2023 Fast and efficient matching algorithm with deadline instances Z Song, W Wang, C Yin, J Yin
arXiv preprint arXiv:2305.08353, 2023
2 2023 
Zhao SongSimons Institute for the Theory of Computing, UC BerkeleyDirección de correo verificada de ias.edu
