Zhengdong Lu 吕正东
ICES postdoctoral fellow, University of Texas at Austin
Email:
Ph.D in Computer Science, OHSU (Thesis advisor: Todd K. Leen)
Clustering with Multiple Graphs. W. Tang, Z. Lu, and I. Dhillon.
ICDM, 2009
A Spatio-Temporal Approach to Collaborative Filtering. Z. Lu, D. Agarwal, and I. Dhillon.
RecSys, 2009
Geometry-aware Metric Learning. Z. Lu, P. Jain, and I. Dhillon. ICML 2009
Research Interests:
I am interested in (almost) all aspects of statistical machine learning, especially in semi-supervised learning, kernel methods, Gaussian processes, and manifold learning. My research has been focused along several threads in adaptive systems including machine learning research in theory and algorithm synthesis, with applications to health care, computer vision, environmental forecasting, and data mining.
| Constrained Clustering (collaborators: Todd K. Leen, Miguel Á. Carreira-Perpiñá) |
Constrained Spectral Clustering with Affinity Propagation. Zhengdong Lu and Miguel Á. Carreira-Perpiñán. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008) (Matlab code)
Penalized Probabilistic Clustering Zhengdong Lu and Todd K. Leen. Neural Computation, 19, 1528-1567, 2007.
Semi-supervised Clustering with Pairwise Constraints: A Discriminative Approach. Zhengdong Lu and Todd K. Leen. Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS), Puerto Rico, 2007.
Semi-supervised Learning with Penalized Probabilistic Clustering. Zhengdong Lu and Todd K. Leen. Advances in Neural Information Processing Systems (NIPS 17) 2004 .
| Manifold Learning and Its Applications (collaborators: Miguel Á. Carreira-Perpiñán, Cristian Sminchisescu) |
Dimensionality reduction by unsupervised regression. Miguel Á. Carreira-Perpiñán and Zhengdong Lu. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008).
People Tracking with the Laplacian Eigenmaps Latent Variable Model. Zhengdong Lu, Miguel Á. Carreira-Perpiñán, and Cristian Sminchisescu, Advances in Neural Information Processing Systems (NIPS 20), 2007
The Laplacian Eigenmaps Latent Variable Model. Miguel Á. Carreira-Perpiñán and Zhengdong Lu. Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS), Puerto Rico, 2007
Modeling and Classification of Longitudinal Data
(collaborators:
Todd K. Leen,
Deniz Erdogmus)
|
| Environmental Observation and Forecasting Systems (colaborators: Todd K. Leen, Rudolph van der Merwe, Sergey Frolov, Antonio M. Baptista) |
Sequential Data Assimilation with Sigma-point Kalman Filter on Low-dimensional Manifold. Zhengdong Lu, Rudolph van der Merwe, Todd K. Leen, Sergy Frolov, A.M. Baptista (submitted to Ocean Modeling).
Fast Neural Network Surrogates for Very High Dimensional Physics-based Models in Computational Oceanograph. Rudolph van der Merwe, Todd K. Leen, Zhengdong Lu, Sergy Frolov, andA.M. Baptista. Neural Networks, 20, 462-478, 2007.
Fast data assimilation with model surrogates:application to a highly stratified estuary. Sergy Frolov, Antonio M. Baptista, Zhengdong Lu, Roulph van der Merwe, Todd K. Leen. Ocean Modeling, 2007.
Fast and model-independent data assimilation ofestuarine circulation, using neural networks. Sergy Frolov, Zhengdong Lu, Roulph van der Merwe, Todd K. Leen, and Antonio M. Baptista. in Eos Trans. AGU, 87(36), Ocean Sci. Meet. Suppl, Abstract OS26O-06, Honolulu, HI, 2006.
| Miscellaneous |
The Laplace Approximation of Gaussian Process Mixture. Zhendong Lu. Learning Workshop (Snowbird), 2007