Follow
Tianhao Wang
Tianhao Wang
PhD student, Department of Statistics and Data Science, Yale University
Verified email at yale.edu - Homepage
Title
Cited by
Cited by
Year
What Happens after SGD Reaches Zero Loss?--A Mathematical Framework
Z Li, T Wang, S Arora
arXiv preprint arXiv:2110.06914, 2021
732021
Provably efficient reinforcement learning with linear function approximation under adaptivity constraints
T Wang, D Zhou, Q Gu
Advances in Neural Information Processing Systems 34, 13524-13536, 2021
412021
Variance-aware off-policy evaluation with linear function approximation
Y Min, T Wang, D Zhou, Q Gu
Advances in neural information processing systems 34, 7598-7610, 2021
342021
Learning stochastic shortest path with linear function approximation
Y Min, J He, T Wang, Q Gu
International Conference on Machine Learning, 15584-15629, 2022
302022
Universality of approximate message passing algorithms and tensor networks
T Wang, X Zhong, Z Fan
arXiv preprint arXiv:2206.13037, 2022
292022
A simple and provably efficient algorithm for asynchronous federated contextual linear bandits
J He, T Wang, Y Min, Q Gu
Advances in neural information processing systems 35, 4762-4775, 2022
272022
Accelerated stochastic mirror descent: From continuous-time dynamics to discrete-time algorithms
P Xu, T Wang, Q Gu
International Conference on Artificial Intelligence and Statistics, 1087-1096, 2018
232018
Continuous and discrete-time accelerated stochastic mirror descent for strongly convex functions
P Xu, T Wang, Q Gu
International Conference on Machine Learning, 5492-5501, 2018
212018
Approximate message passing for orthogonally invariant ensembles: Multivariate non-linearities and spectral initialization
X Zhong, T Wang, Z Fan
arXiv preprint arXiv:2110.02318, 2021
202021
Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model
Z Fan, Y Sun, T Wang, Y Wu
Communications on Pure and Applied Mathematics 76 (6), 1208-1302, 2023
172023
Learn to match with no regret: Reinforcement learning in markov matching markets
Y Min, T Wang, R Xu, Z Wang, M Jordan, Z Yang
Advances in Neural Information Processing Systems 35, 19956-19970, 2022
172022
Implicit bias of gradient descent on reparametrized models: On equivalence to mirror descent
Z Li, T Wang, JD Lee, S Arora
Advances in Neural Information Processing Systems 35, 34626-34640, 2022
162022
Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay
Z Li, T Wang, D Yu
Advances in Neural Information Processing Systems 35, 9233-9248, 2022
112022
Maximum likelihood for high-noise group orbit estimation and single-particle cryo-em
Z Fan, RR Lederman, Y Sun, T Wang, S Xu
The Annals of Statistics 52 (1), 52-77, 2024
102024
Finding regularized competitive equilibria of heterogeneous agent macroeconomic models via reinforcement learning
R Xu, Y Min, T Wang, MI Jordan, Z Wang, Z Yang
International Conference on Artificial Intelligence and Statistics, 375-407, 2023
42023
North American biliary stricture management strategies in children after liver transplantation: a multicenter analysis from the Society of Pediatric Liver Transplantation …
PL Valentino, T Wang, V Shabanova, VL Ng, JC Bucuvalas, AG Feldman, ...
Liver transplantation 28 (5), 819-833, 2022
42022
The marginal value of momentum for small learning rate sgd
R Wang, S Malladi, T Wang, K Lyu, Z Li
arXiv preprint arXiv:2307.15196, 2023
32023
Cooperative multi-agent reinforcement learning: Asynchronous communication and linear function approximation
Y Min, J He, T Wang, Q Gu
International Conference on Machine Learning, 24785-24811, 2023
32023
Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality
S Chen, H Sheen, T Wang, Z Yang
arXiv preprint arXiv:2402.19442, 2024
22024
Noise-Adaptive Thompson Sampling for Linear Contextual Bandits
R Xu, Y Min, T Wang
Advances in Neural Information Processing Systems 36, 2024
12024
The system can't perform the operation now. Try again later.
Articles 1–20