USC Melady Lab

Machine Learning for the real world


The USC Melady Lab develops machine learning and data mining algorithms for solving problems involving data with special structure, including time series, spatiotemporal data, and relational data. We work closely with domain experts to solve challenging problems and make significant impacts in computational biology, social media analysis, climate modeling, health care, and business intelligence.


Rose's paper on Geographic Segmentation via Latent Poisson Factor Model was accepted to WSDM 2016.

Rose's paper on Learning from Multiway Data: Simple and Efficient Tensor Regression was accepted to ICML 2016.

Zhengping's paper on Interpretable Deep Models for ICU Outcome Prediction was accepted to AMIA 2016.

Yan held Mining and Learning from Time Series Workshop at SIGKDD 2016.

Xinran's paper on Learning Influence Functions from Incomplete Observations was accepted to NIPS 2016.

Dehua's paper on SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling was accepted to NIPS 2016.

Yan is offering the class CSCI-567 Machine Learning in the Fall 2016 semester.

Rose will join Stanford University as a visiting student in the Fall 2016

Zhengping will join Mayo Clinic as a visiting student in the Fall 2016