Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms

@inproceedings{Joulani2016DelayTolerantOC,
  title={Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms},
  author={Pooria Joulani and Andr{\'a}s Gy{\"o}rgy and Csaba Szepesv{\'a}ri},
  booktitle={AAAI},
  year={2016}
}
We present a unified, black-box-style method for developing and analyzing online convex optimization (OCO) algorithms for full-information online learning in delayed-feedback environments. Our new, simplified analysis enables us to substantially improve upon previous work and to solve a number of open problems from the literature. Specifically, we develop and analyze asynchronous AdaGrad-style algorithms from the Follow-the-Regularized-Leader (FTRL) and MirrorDescent family that, unlike… CONTINUE READING
10 Citations
18 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Delay-tolerant online convex optimization: Unified analysis and adaptive-gradient algorithms

  • P. Joulani, A. György, C. Szepesvári
  • Url: http://ualberta.ca/ ̃joulani/publications…
  • 2015
3 Excerpts

Similar Papers

Loading similar papers…