Skip to yearly menu bar Skip to main content


Poster

Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization

Baojian Zhou · Feng Chen · Yiming Ying

Pacific Ballroom #92

Keywords: [ Networks and Relational Learning ] [ Non-convex Optimization ] [ Sparsity and Compressed Sensing ]


Abstract: Stochastic optimization algorithms update models with cheap per-iteration costs sequentially, which makes them amenable for large-scale data analysis. Such algorithms have been widely studied for structured sparse models where the sparsity information is very specific, e.g., convex sparsity-inducing norms or $\ell^0$-norm. However, these norms cannot be directly applied to the problem of complex (non-convex) graph-structured sparsity models, which have important application in disease outbreak and social networks, etc. In this paper, we propose a stochastic gradient-based method for solving graph-structured sparsity constraint problems, not restricted to the least square loss. We prove that our algorithm enjoys a linear convergence up to a constant error, which is competitive with the counterparts in the batch learning setting. We conduct extensive experiments to show the efficiency and effectiveness of the proposed algorithms.

Live content is unavailable. Log in and register to view live content