Mengdi Wang
Mengdi Wang
Center for Statistics and Machine Learning, Electrical Engineering, Princeton University; Google
Verified email at - Homepage
Cited by
Cited by
Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
M Wang, EX Fang, H Liu
Mathematical Programming 161 (1-2), 419-449, 2017
Stochastic first-order methods with random constraint projection
M Wang, DP Bertsekas
SIAM Journal on Optimization 26 (1), 681-717, 2016
Near-optimal time and sample complexities for solving Markov decision processes with a generative model
A Sidford, M Wang, X Wu, L Yang, Y Ye
Advances in Neural Information Processing Systems, 5186-5196, 2018
Accelerating stochastic composition optimization
M Wang, J Liu, EX Fang
The Journal of Machine Learning Research 18 (1), 3721-3743, 2017
Variance reduced value iteration and faster algorithms for solving markov decision processes
A Sidford, M Wang, X Wu, Y Ye.
Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete …, 2017
Near-optimal stochastic approximation for online principal component estimation
CJ Li, M Wang, H Liu, T Zhang
Mathematical Programming 167 (1), 75-97, 2018
A distributed tracking algorithm for reconstruction of graph signals
X Wang, M Wang, Y Gu
IEEE Journal of Selected Topics in Signal Processing 9 (4), 728-740, 2015
Stochastic primal-dual methods and sample complexity of reinforcement learning
Y Chen, M Wang
arXiv preprint arXiv:1612.02516, 2016
Finite-sum composition optimization via variance reduced gradient descent
X Lian, M Wang, J Liu
Artificial Intelligence and Statistics. 2017., 2016
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound
LF Yang, M Wang
arXiv preprint arXiv:1905.10389, 2019
Sample-optimal parametric q-learning using linearly additive features
LF Yang, M Wang
arXiv preprint arXiv:1902.04779, 2019
Incremental constraint projection methods for variational inequalities
M Wang, DP Bertsekas
Mathematical Programming 150 (2), 321-363, 2015
Scalable Bilinear Learning Using State and Action Features
Y Chen, L Li, M Wang
International Conference on Machine Learning, 2018
Randomized linear programming solves the Markov decision problem in nearly linear (sometimes sublinear) time
M Wang
Mathematics of Operations Research 45 (2), 517-546, 2020
Primal-Dual Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems
M Wang
arXiv preprint arXiv:1710.06100, 2017
Averaging random projection: A fast online solution for large-scale constrained stochastic optimization
J Liu, Y Gu, M Wang
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
An online primal-dual method for discounted Markov decision processes
M Wang, Y Chen
2016 IEEE 55th Conference on Decision and Control (CDC), 4516-4521, 2016
Strong NP-hardness result for regularized Lq-minimization problems with concave penalty functions
D Ge, Z Wang, Y Ye, H Yin
arXiv preprint arXiv:1501.00622, 2015
Stabilization of stochastic iterative methods for singular and nearly singular linear systems
M Wang, DP Bertsekas
Mathematics of Operations Research 39 (1), 1-30, 2014
Variance reduction methods for sublinear reinforcement learning
S Kakade, M Wang, LF Yang
arXiv preprint arXiv:1802.09184, 2018
The system can't perform the operation now. Try again later.
Articles 1–20