Communication-Avoiding Optimization Methods for Massive-Scale Graphical Model Structure Learning
share
Undirected graphical models compactly represent the structure of large, high-dimensional data sets, which are especially important in interpreting complex scientific data. Some data sets may run to multiple terabytes, and current methods are intractable in both memory size and running time. We introduce HP-CONCORD, a highly scalable optimization algorithm to estimate a sparse inverse covariance matrix based on a regularized pseudolikelihood framework. Our parallel proximal gradient method runs across a multi-node cluster and achieves parallel scalability using a novel communication-avoiding linear algebra algorithm. We demonstrate scalability on problems with 1.28 million dimensions (over 800 billion parameters) and show that it can outperform a previous method on a single node and scales to 1K nodes (24K cores). We use HP-CONCORD to estimate the underlying conditional dependency structure of the brain from fMRI data and use the result to automatically identify functional regions. The results show good agreement with a state-of-the-art clustering from the neuroscience literature.
READ FULL TEXT
