论文信息 - Decision Making with Hierarchical Credal Sets

Decision Making with Hierarchical Credal Sets

We elaborate on hierarchical credal sets, which are sets of probability mass functions paired with second-order distributions. A new criterion to make decisions based on these models is proposed. This is achieved by sampling from the set of mass functions and considering the Kullback-Leibler divergence from the weighted center of mass of the set. We evaluate this criterion in a simple classification scenario: the results show performance improvements when compared to a credal classifier where the second-order distribution is not taken into account.

[1] László Lovász,et al. Hit-and-run mixes fast , 1999, Math. Program..

[2] P. Walley. Inferences from Multinomial Data: Learning About a Bag of Marbles , 1996 .

[3] Alexander Karlsson,et al. Evaluation of Evidential Combination Operators , 2013 .

[4] Luis M. de Campos,et al. Probability Intervals: a Tool for uncertain Reasoning , 1994, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[5] Glenn Shafer,et al. A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[6] Denis Deratani Mauá,et al. Evaluating credal classifiers by utility-discounted predictive accuracy , 2012, Int. J. Approx. Reason..

[7] Andrés Cano,et al. Convex Sets Of Probabilities Propagation By Simulated Annealing , 1994 .

[8] David Sundgren,et al. Second-Order Credal Combination of Evidence , 2013 .

[9] P. Walley. Statistical Reasoning with Imprecise Probabilities , 1990 .

[10] Tommi Tervonen,et al. Hit-And-Run enables efficient weight generation for simulation-based multiple criteria decision analysis , 2013, Eur. J. Oper. Res..

[11] Anne Lohrli. Chapman and Hall , 1985 .

[12] P. Gärdenfors,et al. Unreliable probabilities, risk taking, and decision making , 1982, Synthese.

[13] David Sundgren,et al. On Dependence in Second-Order Probability , 2012, SUM.