Predicting nearly as well as the best pruning of a planar decision graph

We design efficient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.

[1]  S. Vajda,et al.  Integer Programming and Network Flows , 1970 .

[2]  Eugene L. Lawler,et al.  The recognition of Series Parallel digraphs , 1979, SIAM J. Comput..

[3]  Refael Hassin,et al.  Maximum Flow in (s, t) Planar Networks , 1981, Inf. Process. Lett..

[4]  L. R. Rabiner,et al.  An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[5]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[6]  Manfred K. Warmuth,et al.  The weighted majority algorithm , 1989, 30th Annual Symposium on Foundations of Computer Science.

[7]  Vladimir Vovk,et al.  Aggregating strategies , 1990, COLT '90.

[8]  Anna Lubiw,et al.  Upward Planar Drawing of Single Source Acyclic Digraphs , 1991, Planar Graphs.

[9]  Wray L. Buntine,et al.  Learning classification trees , 1992 .

[10]  David Haussler,et al.  How to use expert advice , 1993, STOC.

[11]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[12]  Frans M. J. Willems,et al.  The context-tree weighting method: basic properties , 1995, IEEE Trans. Inf. Theory.

[13]  Manfred K. Warmuth,et al.  Additive versus exponentiated gradient updates for linear prediction , 1995, STOC '95.

[14]  Robert E. Schapire,et al.  Predicting Nearly as Well as the Best Pruning of a Decision Tree , 1995, COLT.

[15]  Vladimir Vovk,et al.  A game of prediction with expert advice , 1995, COLT '95.

[16]  Yoram Singer,et al.  Using and combining predictors that specialize , 1997, STOC '97.

[17]  W. Maass,et al.  Eecient Learning with Virtual Threshold Gates , 1997 .

[18]  Yoram Singer,et al.  An efficient extension to mixture techniques for prediction and decision trees , 1997, COLT '97.

[19]  Manfred K. Warmuth,et al.  Efficient Learning With Virtual Threshold Gates , 1995, Inf. Comput..

[20]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[21]  Manfred K. Warmuth,et al.  Averaging Expert Predictions , 1999, EuroCOLT.

[22]  Manfred K. Warmuth,et al.  Direct and Indirect Algorithms for On-line Learning of Disjunctions , 1999, EuroCOLT.

[23]  Vladimir Vovk,et al.  Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme , 2001, Theor. Comput. Sci..