If you made any changes in Pure, your changes will be visible here soon.

Personal profile

Research Interests

As a computer scientist and statistician, I use computation and data as a lens to explore science and intelligence. To make progress, I examines this with the point of view provided by the twin windows of modern nonparametric method and probabilistic graphical model. My specific research focuses on nonparametric structure learning and representation learning. Success on this research has the potential to revolutionarize the foundation of the second generation of artificial intelligence (i.e., statistical machine learning) and push the frontier of the third generation of artificial intelligence (i.e., deep learning). My applied research interest is to develop a unified set of computational, statistical, and software tools to extract and interpret significant information from the data collected from a variety of scientific areas.

Education/Academic qualification

Machine Learning and Statistics, PhD, Carnegie Mellon University

Fingerprint Dive into the research topics where Han Liu is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

  • 1 Similar Profiles
High-dimensional Mathematics
Graphical Models Mathematics
Parameter estimation Engineering & Materials Science
Principal component analysis Engineering & Materials Science
Estimator Mathematics
Lasso Mathematics
Discriminant analysis Engineering & Materials Science
Rate of Convergence Mathematics

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Grants 2017 2020

Learning systems
Deep neural networks
Education
Testing
Biomarkers
Big data
Parameter estimation
Learning systems
Big data
Distributed computer systems
Statistics
Public health
Principal component analysis
Unsupervised learning
Supervised learning
Learning systems
Mirrors
Statistics
Graph in graph theory
High-dimensional
Turing Machine
Maximum Degree

Research Output 2004 2019

1 Citation (Scopus)

An extreme-value approach for testing the equality of large U-statistic based correlation matrices

Zhou, C., Han, F., Zhang, X. S. & Liu, H., May 1 2019, In : Bernoulli. 25, 2, p. 1472-1503 32 p.

Research output: Contribution to journalArticle

U-statistics
Correlation Matrix
Extreme Values
Equality
Testing
1 Citation (Scopus)

Combinatorial inference for graphical models

Neykov, M., Lu, J. & Liu, H., Apr 1 2019, In : Annals of Statistics. 47, 2, p. 795-827 33 p.

Research output: Contribution to journalArticle

Graphical Models
Testing
Graph in graph theory
Lower bound
Graph Connectivity

Efficient, certifiably optimal clustering with applications to latent variable graphical models

Eisenach, C. & Liu, H., Jul 1 2019, In : Mathematical Programming. 176, 1-2, p. 137-173 37 p.

Research output: Contribution to journalArticle

Latent Variable Models
Semidefinite Programming
Graphical Models
Computational complexity
Semidefinite Programming Relaxation

Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization

Li, X., Lu, J., Arora, R., Haupt, J., Liu, H., Wang, Z. & Zhao, T., Jun 1 2019, In : IEEE Transactions on Information Theory. 65, 6, p. 3489-3514 26 p., 8675509.

Research output: Contribution to journalArticle

Global optimization
Factorization
neural network
Learning systems
guarantee
1 Citation (Scopus)

A convex formulation for high-dimensional sparse sliced inverse regression

Tan, K. M., Wang, Z., Zhang, T., Liu, H. & Cook, R. D., Dec 1 2018, In : Biometrika. 105, 4, p. 769-782 14 p.

Research output: Contribution to journalArticle

Sliced Inverse Regression
Convex optimization
Covariates
High-dimensional
multipliers