The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform

Tianyu Zhang - One of the best experts on this subject based on the ideXlab platform.

Sever S Dragomir - One of the best experts on this subject based on the ideXlab platform.

Alex Olshevsky - One of the best experts on this subject based on the ideXlab platform.

  • stochastic gradient push for strongly Convex Functions on time varying directed graphs
    IEEE Transactions on Automatic Control, 2016
    Co-Authors: Angelia Nedic, Alex Olshevsky
    Abstract:

    We investigate the convergence rate of the recently proposed subgradient-push method for distributed optimization over time-varying directed graphs. The subgradient-push method can be implemented in a distributed way without requiring knowledge of either the number of agents or the graph sequence; each node is only required to know its out-degree at each time. Our main result is a convergence rate of $O((\ln t)/t)$ for strongly Convex Functions with Lipschitz gradients even if only stochastic gradient samples are available; this is asymptotically faster than the $O((\ln t)/\sqrt{t})$ rate previously known for (general) Convex Functions.

  • stochastic gradient push for strongly Convex Functions on time varying directed graphs
    arXiv: Optimization and Control, 2014
    Co-Authors: Angelia Nedic, Alex Olshevsky
    Abstract:

    We investigate the convergence rate of the recently proposed subgradient-push method for distributed optimization over time-varying directed graphs. The subgradient-push method can be implemented in a distributed way without requiring knowledge of either the number of agents or the graph sequence; each node is only required to know its out-degree at each time. Our main result is a convergence rate of $O \left((\ln t)/t \right)$ for strongly Convex Functions with Lipschitz gradients even if only stochastic gradient samples are available; this is asymptotically faster than the $O \left((\ln t)/\sqrt{t} \right)$ rate previously known for (general) Convex Functions.

P Gochhayat - One of the best experts on this subject based on the ideXlab platform.

Angelia Nedic - One of the best experts on this subject based on the ideXlab platform.

  • stochastic gradient push for strongly Convex Functions on time varying directed graphs
    IEEE Transactions on Automatic Control, 2016
    Co-Authors: Angelia Nedic, Alex Olshevsky
    Abstract:

    We investigate the convergence rate of the recently proposed subgradient-push method for distributed optimization over time-varying directed graphs. The subgradient-push method can be implemented in a distributed way without requiring knowledge of either the number of agents or the graph sequence; each node is only required to know its out-degree at each time. Our main result is a convergence rate of $O((\ln t)/t)$ for strongly Convex Functions with Lipschitz gradients even if only stochastic gradient samples are available; this is asymptotically faster than the $O((\ln t)/\sqrt{t})$ rate previously known for (general) Convex Functions.

  • stochastic gradient push for strongly Convex Functions on time varying directed graphs
    arXiv: Optimization and Control, 2014
    Co-Authors: Angelia Nedic, Alex Olshevsky
    Abstract:

    We investigate the convergence rate of the recently proposed subgradient-push method for distributed optimization over time-varying directed graphs. The subgradient-push method can be implemented in a distributed way without requiring knowledge of either the number of agents or the graph sequence; each node is only required to know its out-degree at each time. Our main result is a convergence rate of $O \left((\ln t)/t \right)$ for strongly Convex Functions with Lipschitz gradients even if only stochastic gradient samples are available; this is asymptotically faster than the $O \left((\ln t)/\sqrt{t} \right)$ rate previously known for (general) Convex Functions.