Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Nonconvex Sparsity Optimization

@inproceedings{Lu2014ProximalIR,
  title={Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Nonconvex Sparsity Optimization},
  author={Canyi Lu and Yunchao Wei and Zhouchen Lin and Shuicheng Yan},
  booktitle={AAAI},
  year={2014}
}
min x∈Rn λ〈w,g(x)〉 + 1 2 ||x− b||2, is convex and can be cheaply solved for any given nonnegative w ∈ Rd. Examples: |x| (absolute value of x element-wise). C3h(x) is continuously differentiable with Lipschitz continuous gradient ||∇h(x)−∇h(y)|| ≤ L(h)||x− y|| for any x,y ∈ Rn, L(h) > 0 is called the Lipschitz constant of ∇h. Examples: squared loss and logistic loss. C4λf (g(x)) + h(x)→∞ iff ||x||2→∞; 

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…