A double incremental aggregated gradient method with linear convergence rate for large-scale optimization

Aryan Mokhtari; Mert Gürbüzbalaban; Alejandro Ribeiro

doi:10.1109/ICASSP.2017.7953047

Conference paper, 2017

A double incremental aggregated gradient method with linear convergence rate for large-scale optimization

Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4696–4700, 2017.

Publisher (DOI)

In brief

The conference version of the double incremental aggregated gradient method: an incremental method that aggregates both gradients and iterates over a fixed cycle through the component functions and converges linearly on strongly convex finite sums, with a rate that improves on gradient descent’s.

Topics

Incremental methods & data ordering

Cite

@inproceedings{mokhtari2017diag,
  title   = {A double incremental aggregated gradient method with linear convergence rate for large-scale optimization},
  author  = {Aryan Mokhtari and Mert Gürbüzbalaban and Alejandro Ribeiro},
  year    = {2017},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages   = {4696--4700},
  doi     = {10.1109/ICASSP.2017.7953047},
}