Search Machine Learning Repository: @inproceedings{icml2014c1_lin14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {An Adaptive Accelerated Proximal Gradient Method and its Homotopy Continuation for Sparse Optimization},
    Url = {http://jmlr.org/proceedings/papers/v32/lin14.pdf},
    Abstract = {We first propose an adaptive accelerated proximal gradient(APG) method for minimizing strongly convex composite functions with unknown convexity parameters. This method incorporates a restarting scheme to automatically estimate the strong convexity parameter and achieves a nearly optimal iteration complexity. Then we consider the ℓ1-regularized least-squares (ℓ1-LS) problem in the high-dimensional setting. Although such an objective function is not strongly convex, it has restricted strong convexity over sparse vectors. We exploit this property by combining the adaptive APG method with a homotopy continuation scheme, which generates a sparse solution path towards optimality. This method obtains a global linear rate of convergence and its overall iteration complexity has a weaker dependency on the restricted condition number than previous work.},
    Author = {Qihang Lin and Lin Xiao},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {73-81}
   }