The Experts below are selected from a list of 590877 Experts worldwide ranked by ideXlab platform

Jose C Principe - One of the best experts on this subject based on the ideXlab platform.

  • An Analysis of the Value of Information When Exploring Stochastic, Discrete Multi-Armed Bandits
    Entropy, 2018
    Co-Authors: Isaac J. Sledge, Jose C Principe
    Abstract:

    In this paper, we propose an Information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of Information criterion. This criterion measures the trade-off between Policy Information and obtainable rewards. High amounts of Policy Information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of Policy Information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We demonstrate that a simulated-annealing-like update of this parameter, with a sufficiently fast cooling schedule, leads to a regret that is logarithmic with respect to the number of arm pulls.

  • Using the Value of Information to Explore Stochastic, Discrete Multi-Armed Bandits
    arXiv:1710.02869 [cs stat], 2017
    Co-Authors: Isaac J. Sledge, Jose C Principe
    Abstract:

    In this paper, we propose an Information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of Information criterion. This criterion measures the trade-off between Policy Information and obtainable rewards. High amounts of Policy Information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of Policy Information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We demonstrate that a simulated-annealing-like update of this parameter, with a sufficiently fast cooling schedule, leads to an optimal regret that is logarithmic with respect to the number of episodes.

Isaac J. Sledge - One of the best experts on this subject based on the ideXlab platform.

  • An Analysis of the Value of Information When Exploring Stochastic, Discrete Multi-Armed Bandits
    Entropy, 2018
    Co-Authors: Isaac J. Sledge, Jose C Principe
    Abstract:

    In this paper, we propose an Information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of Information criterion. This criterion measures the trade-off between Policy Information and obtainable rewards. High amounts of Policy Information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of Policy Information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We demonstrate that a simulated-annealing-like update of this parameter, with a sufficiently fast cooling schedule, leads to a regret that is logarithmic with respect to the number of arm pulls.

  • Using the Value of Information to Explore Stochastic, Discrete Multi-Armed Bandits
    arXiv:1710.02869 [cs stat], 2017
    Co-Authors: Isaac J. Sledge, Jose C Principe
    Abstract:

    In this paper, we propose an Information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of Information criterion. This criterion measures the trade-off between Policy Information and obtainable rewards. High amounts of Policy Information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of Policy Information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We demonstrate that a simulated-annealing-like update of this parameter, with a sufficiently fast cooling schedule, leads to an optimal regret that is logarithmic with respect to the number of episodes.

Scott A Mackenzie - One of the best experts on this subject based on the ideXlab platform.

  • informing the electorate how party cues and Policy Information affect public opinion about initiatives
    American Journal of Political Science, 2014
    Co-Authors: Cheryl Boudreau, Scott A Mackenzie
    Abstract:

    Citizens in representative democracies receive party endorsements and Policy Information when choosing candidates or making Policy decisions via the initiative process. What effects do these sources of Information have on public opinion? We address this important question by conducting survey experiments where citizens express opinions about initiatives in a real-world electoral context. We manipulate whether they receive party cues, Policy Information, both, or neither type of Information. We find that citizens do not simply ignore Policy Information when they are also exposed to party cues. Rather, citizens respond by shifting their opinions away from their party's positions when Policy Information provides a compelling reason for doing so. These results challenge the prominent claim in public opinion research that citizens blindly follow their party when also exposed to Policy Information. They also suggest that efforts to inform the electorate can influence opinions, provided that citizens actually receive the Information being disseminated.

Cheryl Boudreau - One of the best experts on this subject based on the ideXlab platform.

  • informing the electorate how party cues and Policy Information affect public opinion about initiatives
    American Journal of Political Science, 2014
    Co-Authors: Cheryl Boudreau, Scott A Mackenzie
    Abstract:

    Citizens in representative democracies receive party endorsements and Policy Information when choosing candidates or making Policy decisions via the initiative process. What effects do these sources of Information have on public opinion? We address this important question by conducting survey experiments where citizens express opinions about initiatives in a real-world electoral context. We manipulate whether they receive party cues, Policy Information, both, or neither type of Information. We find that citizens do not simply ignore Policy Information when they are also exposed to party cues. Rather, citizens respond by shifting their opinions away from their party's positions when Policy Information provides a compelling reason for doing so. These results challenge the prominent claim in public opinion research that citizens blindly follow their party when also exposed to Policy Information. They also suggest that efforts to inform the electorate can influence opinions, provided that citizens actually receive the Information being disseminated.

Choong Seon Hong - One of the best experts on this subject based on the ideXlab platform.

  • A network management Architecture using XML-based Policy Information base
    Lecture Notes in Computer Science, 2003
    Co-Authors: Kwoun Sup Youn, Choong Seon Hong
    Abstract:

    XML is being used to describe components and applications in a vendor and language neutral. Therefore it already has a role in distributed system. XML is also being used as a data interchange format between components and applications in loosely coupled large-scale application. Until now, Policy is described for specific applications and devices. Its use has been very limited. In current network management system, we can only invoke predefined operations and actions using Policy-based Network Management. The main motivation for the recent interests in Policy-based networks is to support dynamic adaptability of behavior by changing Policy without recoding or stopping system. For these reasons we present the use of the XML for describing the Policy and PIB(Policy Information Base) in COPS-PR. It improves flexibility and interoperability among heterogeneous network systems. It also can add new functionality into network components. In this paper, we propose a network management Architecture using XML-based Policy Information base.

  • ICOIN - A Network Management Architecture Using XML-Based Policy Information Base
    Information Networking, 2003
    Co-Authors: Kwoun Sup Youn, Choong Seon Hong
    Abstract:

    XML is being used to describe components and applications in a vendor and language neutral. Therefore it already has a role in distributed system. XML is also being used as a data interchange format between components and applications in loosely coupled large-scale application. Until now, Policy is described for specific applications and devices. Its use has been very limited. In current network management system, we can only invoke predefined operations and actions using Policy-based Network Management. The main motivation for the recent interests in Policy-based networks is to support dynamic adaptability of behavior by changing Policy without recoding or stopping system. For these reasons we present the use of the XML for describing the Policy and PIB(Policy Information Base) in COPS-PR. It improves flexibility and interoperability among heterogeneous network systems. It also can add new functionality into network components. In this paper, we propose a network management Architecture using XML-based Policy Information base.