Tianhao Wang

According to our database, Tianhao Wang authored at least 7 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

How Well Can Transformers Emulate In-context Newton's Method?

Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris Papailiopoulos, Jason D. Lee

CoRR, 2024

The Marginal Value of Momentum for Small Learning Rate SGD.

Runzhe Wang, Sadhika Malladi, Tianhao Wang, Kaifeng Lyu, Zhiyuan Li

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2022

Universality of Approximate Message Passing algorithms and tensor networks.

Tianhao Wang, Xinyi Zhong, Zhou Fan

CoRR, 2022

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay.

Zhiyuan Li, Tianhao Wang, Dingli Yu

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent.

Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

What Happens after SGD Reaches Zero Loss? --A Mathematical Framework.

Zhiyuan Li, Tianhao Wang, Sanjeev Arora

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM.

Zhou Fan, Roy R. Lederman, Yi Sun, Tianhao Wang, Sheng Xu

CoRR, 2021