Package InfoCollection.util

Examples of InfoCollection.util.MeanVariance

44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
   * repeats the experiment, returning a sample average. The other runs the
   * experiment once and returns the loss realized.
   */
  public static double LossAtEnd(SamplingRule policy, Truth truth, int N,
      int nruns) throws Exception {
    MeanVariance lossEstimator = new MeanVariance();
    Random rnd = new Random();
    for (int r = 0; r < nruns; r++) {
      policy.Start(truth.M());
      for (int n = 0; n < N; n++) {
        int x = policy.GetMeasurementDecision();
        double y = truth.Sample(x, rnd);
        policy.RecordMeasurement(x, y);
      }
      int i = policy.GetImplementationDecision();
      lossEstimator.AddSample(truth.Loss(i));
    }
    return lossEstimator.SampleMean();
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
   * from the belief b. Also note that it returns a MeanVariance, rather than
   * just the sample average.
   */
  public static MeanVariance LossAtEnd(SamplingRule policy, Belief b, int N,
      int nruns) throws Exception {
    MeanVariance lossEstimator = new MeanVariance();
    Random rnd = new Random();
    for (int r = 0; r < nruns; r++) {
      Truth truth = b.GenerateTruth(rnd);
      policy.Start(truth.M());
      for (int n = 0; n < N; n++) {
        int x = policy.GetMeasurementDecision();
        double y = truth.Sample(x, rnd);
        policy.RecordMeasurement(x, y);
      }
      int i = policy.GetImplementationDecision();
      lossEstimator.AddSample(truth.Loss(i));
    }
    return lossEstimator;
  }
View Full Code Here
120
121
122
123
124
125
126
127
128
129
130
131
    MeanVariance[] loss = new MeanVariance[stop.Length()];
    MeanVariance[] N = new MeanVariance[stop.Length()];
    double[][] result = new double[stop.Length()][5];
    for (s = 0; s < stop.Length(); s++) {
      timeouts[s] = 0;
      loss[s] = new MeanVariance();
      N[s] = new MeanVariance();
    }

    Random rnd = new Random();
    for (r = 0; r < nruns; r++) {
      policy.Start(truth.M());
View Full Code Here
208
209
210
211
212
213
214
215
216
217
218
219
    MeanVariance[] loss = new MeanVariance[stop.Length()];
    MeanVariance[] N = new MeanVariance[stop.Length()];
    double[][] result = new double[stop.Length()][5];
    for (s = 0; s < stop.Length(); s++) {
      timeouts[s] = 0;
      loss[s] = new MeanVariance();
      N[s] = new MeanVariance();
    }

    Random rnd = new Random();
    for (r = 0; r < nruns; r++) {
      Truth truth = prior.GenerateTruth(rnd);
View Full Code Here
260
261
262
263
264
265
266
267
268
269
270
271
272
  // that class.
  public MeanVariance EOCBayesMC(int nsamples, Random rnd)
      throws NotInformativeException {
    // int M = mu.length;
    // double[] values = new double[M];
    MeanVariance ans = new MeanVariance();
    double maxmu = MathPF.max(mu);
    for (int s = 0; s < nsamples; s++) {
      Truth truth = GenerateTruth(rnd);
      ans.AddSample(truth.BestValue() - maxmu);
    }
    return ans;
  }
View Full Code Here
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
    /* Evaluate using numerical integration and monte carlo. */
    double EOCBayesAns = EOCBayes();
    int mcsamples = 1000000;
    try {
      MeanVariance MCAns = EOCBayesMC(mcsamples);

      /* Get the t-statistic and report the result. */
      double t = (EOCBayesAns - MCAns.SampleMean())
          / MCAns.SampleMeanDeviation();
      if (verbose)
        System.out.printf(
            "EOCBayes Answer=%f, MonteCarlo Answer=%f, t=%f\n",
            EOCBayesAns, MCAns, t);
      return t;
View Full Code Here
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
   * Tests that the computation of sigmahat is correct.
   */
  public static boolean test1() {
    try {
      int N = 1000;
      MeanVariance mv = new MeanVariance();
      Random rnd = new Random();
      Belief b = new Belief(1);
      for (int n = 0; n < N; n++) {
        double data = rnd.nextGaussian();
        b.Update(0, data);
        mv.AddSample(data);
      }
      /*
       * Now, SampleVarianceMSE(), which computes sigmahat^2, should be
       * equal to sigmahat^2 as computed by Belief.
       */
      double mv_val = mv.SampleVarianceMSE();
      double b_val = b.sigmahat2(0);
      int ulps = MathPF.FloatCmp(mv_val, b_val);
      boolean ok = ulps < 30;
      System.out.printf("test1: diff/ulp=%d (true)variance=1 "
          + "MeanVariance.sigmahat=%.3f belief.sigmahat=%.3f\n",
          ulps, mv.SampleVarianceMSE(), b.sigmahat2(0));
      if (ok)
        System.out.println("test1: OK");
      else
        System.out.println("test1: FAILED");
      return ok;
View Full Code Here
TOP

Related Classes of InfoCollection.util.MeanVariance

  • InfoCollection.IndependentNormalVarianceKnown.Belief
  • InfoCollection.IndependentNormalVarianceUnknown.Belief
  • InfoCollection.Simulator
  • java.util.Random
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.