Here is my Google Scholar page and my Research Blog.
Email: songmei@berkeley.edu
Office: Evans 387.
Our goal is to develop efficient algorithms for learning equilibria in multi-player games. Applications include real-world games such as Poker, Bridge, and Go, as well as economic systems such as auction and marketing.
Our goal is to theoretically investigate the interplay between convolution structures in neural networks and the image distribution. We explained the mechanism of why convolutional neural networks (kernels) are suitable for image datasets.
We study statistical-computational gaps in high dimensional statistical models.