Tengyuan Liang

Research

Authors list in the alphabetical order.

Interest

  • Primary:

    • Computational Difficulty and Efficiency in Statistics

    • Statistical Learning Theory

    • Stochastic Optimization

  • Secondary: Network Science, High Dimensional Statistics, Online Learning

Manuscript

  • How Well Can Generative Adversarial Networks (GAN) Learn Densities: A Nonparametric View

    • T. Liang

    • submitted (2017)

    • [arxiv]

  • Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients

    • T. Liang and W. Su

    • submitted (2017)

    • [arxiv]

  • Fisher-Rao Metric, Geometry, and Complexity of Neural Networks

    • T. Liang, T. Poggio, A. Rakhlin and J. Stokes

    • submitted (2017)

    • [arxiv]

  • Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information

    • T. Cai, T. Liang and A. Rakhlin

    • submitted (2017)

    • [arxiv]

Peer-Reviewed Publications

  • Computational and Statistical Boundaries for Submatrix Localization in a Large Noisy Matrix

  • Geometric Inference for General High-Dimensional Linear Inverse Problems

  • Law of Log Determinant of Sample Covariance Matrix and Optimal Estimation of Differential Entropy for High-Dimensional Gaussian Distributions

Collaborators






[ Other Writings ]