Прати
Jingzhao Zhang
Jingzhao Zhang
IIIS, Tsinghua University
Верификована је имејл адреса на mit.edu - Почетна страница
Наслов
Навело
Навело
Година
Why gradient clipping accelerates training: A theoretical justification for adaptivity
AJ Jingzhao Zhang, Tianxing He, Suvrit Sra
International Conference on Learning Representations 2020, 2020
571*2020
Why are adaptive methods good for attention models?
J Zhang, SP Karimireddy, A Veit, S Kim, S Reddi, S Kumar, S Sra
Advances in Neural Information Processing Systems 33, 15383-15393, 2020
375*2020
3D computer-generated holography by non-convex optimization
J Zhang, N Pégard, J Zhong, H Adesnik, L Waller
Optica 4 (10), 1306-1313, 2017
2542017
Direct Runge-Kutta Discretization Achieves Acceleration
J Zhang, A Mokhtari, S Sra, A Jadbabaie
Advances in Neural Information Processing Systems 2018, 2018
1272018
Complexity of finding stationary points of nonconvex nonsmooth functions
J Zhang, H Lin, S Jegelka, S Sra, A Jadbabaie
International Conference on Machine Learning, 11173-11182, 2020
1162020
Fast federated learning in the presence of arbitrary device unavailability
X Gu, K Huang, J Zhang, L Huang
Advances in Neural Information Processing Systems 34, 12052-12064, 2021
1082021
Understanding the unstable convergence of gradient descent
K Ahn, J Zhang, S Sra
International conference on machine learning, 247-257, 2022
832022
Coping with label shift via distributionally robust optimisation
J Zhang, A Menon, A Veit, S Bhojanapalli, S Kumar, S Sra
ICLR 2021, 2020
832020
Exposure bias versus self-recovery: Are distortions really incremental for autoregressive text generation?
T He, J Zhang, Z Zhou, J Glass
ACL 2021, 2019
67*2019
Realistic fault detection of li-ion battery via dynamical deep learning
J Zhang, Y Wang, B Jiang, H He, S Huang, C Wang, Y Zhang, X Han, ...
Nature Communications 14 (1), 5940, 2023
542023
Complexity lower bounds for nonconvex-strongly-concave min-max optimization
H Li, Y Tian, J Zhang, A Jadbabaie
Advances in Neural Information Processing Systems 34, 1792-1804, 2021
522021
R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate
J Zhang, H Zhang, S Sra
arXiv preprint arXiv:1811.04194, 2018
422018
On finding small hyper-gradients in bilevel optimization: Hardness results and improved analysis
L Chen, J Xu, J Zhang
The Thirty Seventh Annual Conference on Learning Theory, 947-980, 2024
35*2024
A probe towards understanding gan and vae models
L Mi, M Shen, J Zhang
arXiv preprint arXiv:1812.05676, 2018
342018
Provably efficient algorithms for multi-objective competitive rl
T Yu, Y Tian, J Zhang, S Sra
International Conference on Machine Learning, 12167-12176, 2021
282021
Sion’s minimax theorem in geodesic metric spaces and a Riemannian extragradient algorithm
P Zhang, J Zhang, S Sra
SIAM Journal on Optimization 33 (4), 2885-2908, 2023
25*2023
Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODE
J Zhang, CA Uribe, A Mokhtari, A Jadbabaie
2019 American Control Conference, 2018
232018
Online policy optimization for robust mdp
J Dong, J Li, B Wang, J Zhang
arXiv preprint arXiv:2209.13841, 2022
182022
Efficient sampling on Riemannian manifolds via Langevin MCMC
X Cheng, J Zhang, S Sra
Advances in Neural Information Processing Systems 35, 5995-6006, 2022
15*2022
On the overlooked pitfalls of weight decay and how to mitigate them: A gradient-norm perspective
Z Xie, Z Xu, J Zhang, I Sato, M Sugiyama
Advances in Neural Information Processing Systems 36, 1208-1228, 2023
132023
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–20