Dictionary learning over large distributed models via dual-ADMM strategies

@article{Towfic2014DictionaryLO,
  title={Dictionary learning over large distributed models via dual-ADMM strategies},
  author={Zaid J. Towfic and Jianshu Chen and Ali H. Sayed},
  journal={2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
  year={2014},
  pages={1-6}
}
We consider the problem of dictionary learning over large scale models, where the model parameters are distributed over a multi-agent network. We demonstrate that the dual optimization problem for inference is better conditioned than the primal problem and that the dual cost function is an aggregate of individual costs associated with different network agents. We also establish that the dual cost function is smooth, strongly-convex, and possesses Lipschitz continuous gradients. These properties… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 22 references

Online 1-dictionary learning with application to novel document detection

  • S. P. Kasiviswanathan, H. Wangy, A. Banerjeey, P. Melville
  • Proc. Neural Information Processing Systems (NIPS…
  • 2012
2 Excerpts

Distributed optimization and statistical learning via the alternating direction method of multipliers

  • S. P. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein
  • Foundations and Trends in Machine Learning, vol…
  • 2011
1 Excerpt

Similar Papers

Loading similar papers…