Yifei Wang
 |
Yifei Wang (汪祎非) |
About me
I am a fifth-year Ph.D. candidate in the Department of Electrical Engineering at Stanford University, where I am coadvised by Prof. Mert Pilanci and Prof. David Tse. Prior to joining Stanford, I obtained my B.S. degree of Computational and Applied Mathematics in School of Mathematical Science at Peking University, advised by Prof. Zaiwen Wen. My research interests include applications of convex neural networks on the training of large language model and the design of consensus protocols.
Recent News
2024/06 I start to intern at Apple ASM group. Thanks a lot to Frank and Minda for hosting me.
2024/06 Our paper A Circuit Approach to Constructing Blockchains on Blockchains is accepted at AFT’24. Too long; Don't read (TLDR): we build a more secure overlay blockchain by reading from and writing to a given set of blockchains.
2024/06 Our paper Randomized Geometric Algebra Methods for Convex Neural Networks is available on arxiv. Too long; Don't read (TLDR): We introduce randomized algorithms to Clifford's Geometric Algebra for finetuning Large Language Models.
2024/05 Our paper Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization is accepted at SIAM Journal on Mathematics of Data Science. Too long; Don't read (TLDR): We apply neural networks and convex optimization to approximate Wasserstein Gradient Direction.
2024/03 Our paper A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features is available on arxiv. Too long; Don't read (TLDR): training a neural network on 1D dataset is equivalent to solving a Lasso problem. This extends to deep neural networks up to 4 layer.
Contact
If you find any of my research interesting or have any questions, feel free to reach out to me via email!
Email wangyf18 at stanford dot edu
Pilanci Research Group's Github
CV
Last update
August 23rd, 202