Xiang Cheng
Xiang Cheng
Massachusetts Institute of Technology
Verified email at - Homepage
Cited by
Cited by
Underdamped Langevin MCMC: A non-asymptotic analysis
X Cheng, NS Chatterji, PL Bartlett, MI Jordan
Conference on learning theory, 300-323, 2018
Convergence of Langevin MCMC in KL-divergence
X Cheng, P Bartlett
Algorithmic Learning Theory, 186-211, 2018
Sharp convergence rates for Langevin dynamics in the nonconvex setting
X Cheng, NS Chatterji, Y Abbasi-Yadkori, PL Bartlett, MI Jordan
arXiv preprint arXiv:1805.01648, 2018
Is there an analog of Nesterov acceleration for gradient-based MCMC?
YA Ma, NS Chatterji, X Cheng, N Flammarion, PL Bartlett, MI Jordan
Asymptotic behavior of\ell_p-based laplacian regularization in semi-supervised learning
A El Alaoui, X Cheng, A Ramdas, MJ Wainwright, MI Jordan
Conference on Learning Theory, 879-906, 2016
Optimal dimension dependence of the metropolis-adjusted langevin algorithm
S Chewi, C Lu, K Ahn, X Cheng, T Le Gouic, P Rigollet
Conference on Learning Theory, 1260-1300, 2021
Transformers learn to implement preconditioned gradient descent for in-context learning
K Ahn, X Cheng, H Daneshmand, S Sra
Advances in Neural Information Processing Systems 36, 2024
Stochastic Gradient and Langevin Processes
X Cheng, D Yin, PL Bartlett, MI Jordan
arXiv preprint arXiv:1907.03215, 2019
Exploiting optimization for local graph clustering
K Fountoulakis, X Cheng, J Shun, F Roosta-Khorasani, MW Mahoney
arXiv preprint arXiv:1602.01886, 2016
Restart sampling for improving generative processes
Y Xu, M Deng, X Cheng, Y Tian, Z Liu, T Jaakkola
Advances in Neural Information Processing Systems 36, 76806-76838, 2023
Linear attention is (maybe) all you need (to understand transformer optimization)
K Ahn, X Cheng, M Song, C Yun, A Jadbabaie, S Sra
arXiv preprint arXiv:2310.01082, 2023
Transformers implement functional gradient descent to learn non-linear functions in context
X Cheng, Y Chen, S Sra
arXiv preprint arXiv:2312.06528, 2023
Efficient Sampling on Riemannian Manifolds via Langevin MCMC
X Cheng, J Zhang, S Sra
Advances in Neural Information Processing Systems, 2022
Theory and algorithms for diffusion processes on riemannian manifolds
X Cheng, J Zhang, S Sra
arXiv preprint arXiv:2204.13665, 2022
The Interplay between Sampling and Optimization
X Cheng
University of California, Berkeley, 2020
Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions
X Cheng, B Wang, J Zhang, Y Zhu
Advances in Neural Information Processing Systems 36, 2024
FLAG n’FLARE: Fast Linearly-Coupled Adaptive Gradient Methods
X Cheng, F Roosta, S Palombo, P Bartlett, M Mahoney
International Conference on Artificial Intelligence and Statistics, 404-414, 2018
The system can't perform the operation now. Try again later.
Articles 1–17