Simon Shaolei Du
Simon Shaolei Du
Assistant Professor, School of Computer Science and Engineering, University of Washington
Verified email at cs.washington.edu - Homepage
Title
Cited by
Cited by
Year
Gradient descent provably optimizes over-parameterized neural networks
SS Du, X Zhai, B Poczos, A Singh
International Conference on Learning Representations 2019, 2018
3532018
Gradient descent finds global minima of deep neural networks
SS Du, JD Lee, H Li, L Wang, X Zhai
International Conference on Machine Learning 2019, 2018
3182018
Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks
S Arora, SS Du, W Hu, Z Li, R Wang
International Conference on Machine Learning 2019, 2019
2222019
On exact computation with an infinitely wide neural net
S Arora, SS Du, W Hu, Z Li, RR Salakhutdinov, R Wang
Advances in Neural Information Processing Systems, 8141-8150, 2019
1872019
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
SS Du, JD Lee, Y Tian, B Poczos, A Singh
International Conference on Machine Learning 2018, 2017
1442017
On the power of over-parametrization in neural networks with quadratic activation
SS Du, JD Lee
International Conference on Machine Learning 2018, 2018
1162018
Gradient descent can take exponential time to escape saddle points
SS Du, C Jin, JD Lee, MI Jordan, A Singh, B Poczos
Advances in neural information processing systems, 1067-1077, 2017
1162017
When is a convolutional filter easy to learn?
SS Du, JD Lee, Y Tian
International Conference on Learning Representations 2018, 2017
882017
Stochastic variance reduction methods for policy evaluation
SS Du, J Chen, L Li, L Xiao, D Zhou
International Conference on Machine Learning 2017, 2017
812017
Computationally efficient robust estimation of sparse functionals
SS Du, S Balakrishnan, A Singh
Conference on Learning Theory, 2017, 2017
79*2017
Algorithmic regularization in learning deep homogeneous models: Layers are automatically balanced
SS Du, W Hu, JD Lee
Advances in Neural Information Processing Systems, 384-395, 2018
502018
Understanding the acceleration phenomenon via high-resolution differential equations
B Shi, SS Du, MI Jordan, WJ Su
arXiv preprint arXiv:1810.08907, 2018
462018
Stochastic zeroth-order optimization in high dimensions
Y Wang, S Du, S Balakrishnan, A Singh
International Conference on Artificial Intelligence and Statistics 2018, 2017
452017
Linear convergence of the primal-dual gradient method for convex-concave saddle point problems without strong convexity
SS Du, W Hu
International Conference on Artificial Intelligence and Statistics 2019, 2018
432018
Provably efficient RL with rich observations via latent state decoding
SS Du, A Krishnamurthy, N Jiang, A Agarwal, M Dudík, J Langford
International Conference on Machine Learning 2019, 2019
342019
What Can Neural Networks Reason About?
K Xu, J Li, M Zhang, SS Du, K Kawarabayashi, S Jegelka
International Conference on Learning Representations 2020, 2019
332019
An improved gap-dependency analysis of the noisy power method
MF Balcan, SS Du, Y Wang, AW Yu
Conference on Learning Theory, 284-309, 2016
312016
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
SS Du, K Hou, B Póczos, R Salakhutdinov, R Wang, K Xu
Advances in Neural Information Processing Systems 2019, 2019
292019
Provably efficient Q-learning with function approximation via distribution shift error checking oracle
SS Du, Y Luo, R Wang, H Zhang
Advances in Neural Information Processing Systems, 8060-8070, 2019
262019
How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network?
SS Du, Y Wang, X Zhai, S Balakrishnan, R Salakhutdinov, A Singh
Advances in Neural Information Processing Systems 2018, 2018
25*2018
The system can't perform the operation now. Try again later.
Articles 1–20