[MATH-304] CurveFitter.fit(ParametricRealFunction, double[]) always returns the same value as the initial guess when used with the LevenbergMarquardtOptimizer

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Invalid
• Affects Version/s: 2.0
• Fix Version/s: 2.1

Environment

Java, Ubuntu 9.04 (64 bit)

• Assignee: Unassigned
• Reporter: Daren Drummond
• Created: 19/Oct/09 21:29
• Updated: 14/Apr/10 00:06
• Resolved: 27/Dec/09 17:33

Description

CurveFitter.fit(ParametricRealFunction, double[]) always returns the same value as the initial guess when used with the LevenbergMarquardtOptimizer and the length of the initial guess array is 1. Here is my example code:

CurveFitter with LevenbergMarquardtOptimizer

  LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
  CurveFitter fitter = new CurveFitter(optimizer);
  fitter.addObservedPoint(2.805d, 0.6934785852953367d);
  fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
  fitter.addObservedPoint(1.655d, 0.9474675497289684);
  fitter.addObservedPoint(1.725d, 0.9013594835804194d);
  SimpleInverseFunction sif = new SimpleInverseFunction(); // Class provided below
  double[] initialguess = new double[1];
  initialguess[0] = 1.0d;
  double[] bestCoefficients = fitter.fit(sif, initialguess); // <---- ALWAYS RETURNS A VALUE OF initialguess !

    /**
     * This is my implementation of ParametricRealFunction
     * Implements y = ax^-1 + b for use with an Apache CurveFitter implementation
      */
    private class SimpleInverseFunction implements ParametricRealFunction
    {
        public double value(double x, double[] doubles) throws FunctionEvaluationException
        {
            //y = ax^-1 + b
            //"double[] must include at least 1 but not more than 2 coefficients."
            if(doubles == null || doubles.length ==0 || doubles.length > 2) throw new FunctionEvaluationException(doubles);
            double a = doubles[0];
            double b = 0;
            if(doubles.length >= 2) b = doubles[1];
            return a * Math.pow(x, -1d) + b;
        }
        public double[] gradient(double x, double[] doubles) throws FunctionEvaluationException
        {
            //derivative: -ax^-2
            //"double[] must include at least 1 but not more than 2 coefficients."
            if(doubles == null || doubles.length ==0 || doubles.length > 2) throw new FunctionEvaluationException(doubles);
            double a = doubles[0];
            double b = 0;
            if(doubles.length >= 2) b = doubles[1];
            double derivative = -a * Math.pow(x, -2d);
            double[]gradientVector = new double[1];
            gradientVector[0] = derivative;
            return gradientVector; 
        }
    }