Tianhao Wang (王天浩)
Ph.D. student, Department of Statistics and Data Science, Yale University.
Department of S&DS
219 Prospect Avenue
New Haven, CT 06511
tianhao.wang@yale.edu
I am a final year Ph.D. student in the Department of Statistics and Data Science at Yale University. I am very fortunate to be advised by Prof. Zhou Fan. I am broadly interested in various aspects of statistics and machine learning theory.
Prior to Yale, I obtained my Bachelor’s degree in mathematics with a dual degree in computer science at University of Science and Technology of China.
CVRecent papers(*: equal contribution)
Foundations of Transformers

Implicit regularization of gradient flow on onelayer softmax attentionarXiv:2403.08699, 2024Accepted to ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning

How well can Transformers emulate incontext Newton's method?arXiv:2403.03183, 2024Accepted to ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning

Training dynamics of multihead softmax attention for incontext learning: emergence, convergence, and optimalityarXiv:2402.19442, 2024Accepted to ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning
Approximate Message Passing algorithms
Implicit bias of optimization algorithms

Fast mixing of stochastic gradient descent with normalization and weight decayIn Advances in Neural Information Processing Systems (NeurIPS), 2022

Implicit bias of gradient descent on reparametrized models: On equivalence to mirror descentIn Advances in Neural Information Processing Systems (NeurIPS), 2022Abridged version accepted for a contributed talk to ICML 2022 Workshop on Continuous time methods for machine learning
Datadriven decisionmaking problems

Noiseadaptive Thompson sampling for linear contextual banditsIn Advances in Neural Information Processing Systems (NeurIPS), 2023