Example #1
0
/**  
 *  Compute loss and gradient of Huber hinge loss. 
 *  CAUTION: f is passed by reference and is changed within this
 *  function. This is done for efficiency reasons, otherwise we would
 *  have had to create a new copy of f.
 *   
 *  @param loss [write] loss value computed.
 *  @param f [read/write] prediction vector. 
 *  @param l [write] partial derivative of loss function w.r.t. f
 */
void CHuberHingeLoss::LossAndGrad(double& loss, TheMatrix& f, TheMatrix& l)
{
   f.ElementWiseMult(_data->labels());
   double* yf = f.Data();
   double* Y = _data->labels().Data();
   int len = f.Length();
   loss = 0.0;
   l.Zero();

   for(int i=0; i < len; i++) 
   {
      double v = 1-yf[i];
      if(h < v)
      {
         loss += v;
         l.Set(i,-Y[i]);
      }
      else if(-h > v) {}
      else
      {
         loss += (v+h)*(v+h)/4/h;
         l.Set(i, -Y[i]*(v+h)/2/h);
      }
   }
}
Example #2
0
/**  
 *  Compute loss and partial derivative of hinge loss w.r.t f
 *   
 *  @param loss [write] loss value computed.
 *  @param f [r/w] = X*w
 *  @param l [write] partial derivative of loss w.r.t. f
 */
void CLogisticLoss::LossAndGrad(double& loss, TheMatrix& f, TheMatrix& l)
{
    l.Zero();  // for gradient computation i.e. grad := l'*X
    f.ElementWiseMult(_data->labels());
    double* f_array = f.Data();  // pointer to memory location of f (faster element access)
    int len = f.Length();	
    double exp_yf = 0.0;

    for(int i=0; i < len; i++)
    {
	if(fabs(f_array[i]) == 0.0)
        {
            loss += LN2;
            l.Set(i,-0.5);
        }
        else if (f_array[i] > 0.0)
        {
            exp_yf = exp(-f_array[i]);
            loss += log(1+exp_yf);
            l.Set(i,-exp_yf/(1+exp_yf));
        }
        else
        {
            exp_yf = exp(f_array[i]);
            loss += log(1+exp_yf) - f_array[i];
            l.Set(i,-1.0/(1+exp_yf));
        }
    }	
    l.ElementWiseMult(_data->labels());
}
/**  
 *  Compute NDCGRank loss. CAUTION: f is passed by reference and is
 *  changed within this function. This is done for efficiency reasons,
 *  otherwise we would have had to create a new copy of f. 
 *   
 *  @param loss [write] loss value computed.
 *  @param f [read/write] prediction vector. 
 */
void CNDCGRankLoss::Loss(Scalar& loss, TheMatrix& f)
{
  // chteo: here we make use of the subset information 
        
  loss = 0.0;	
  Scalar* f_array = f.Data();  
  for(int q=0; q < _data->NumOfSubset(); q++)
    {
      int offset = _data->subset[q].startIndex;
      int subsetsize = _data->subset[q].size;
      current_ideal_pi = sort_vectors[q];
      vector<double> b = bs[q];

      //compute_coefficients(offset, subsetsize, y_array, current_ideal_pi, a, b);
      
      /* find the best permutation */
      find_permutation(subsetsize, offset, a, b, c, f_array, pi);
      
      /* compute the loss */
      double value;
      delta(subsetsize, a, b, pi, value);
      
      loss += value;
      
      for (int i=0;i<subsetsize;i++){
	loss = loss + c[i]*(get(f_array, offset, pi[i]) - get(f_array, offset, i));
      }
      //free(c);
      //free(a);
      //free(b);
      //free(pi);
      
    }

}
Example #4
0
/**
 *  Compute loss and gradient of Least Absolute Deviation loss w.r.t f
 *
 *  @param loss [write] loss value computed.
 *  @param f [r/w] = X*w
 *  @param l [write] partial derivative of loss w.r.t. f
 */
void CLeastAbsDevLoss::LossAndGrad(double& loss, TheMatrix& f, TheMatrix& l)
{
    loss = 0;
    l.Zero();
    double *Y_array = _data->labels().Data();
    double* f_array = f.Data();
    int len = f.Length();
    for(int i=0; i < len; i++)
    {
        double f_minus_y = f_array[i] - Y_array[i];
        loss += fabs(f_minus_y);
        l.Set(i, SML::sgn(f_minus_y));
    }
}
Example #5
0
/**  
 *  Compute loss and gradient of novelty detection loss. 
 *  CAUTION: f is passed by reference and is changed within this
 *  function. This is done for efficiency reasons, otherwise we would
 *  have had to create a new copy of f.
 *   
 *  @param loss [write] loss value computed.
 *  @param f [read/write] prediction vector. 
 *  @param l [write] partial derivative of loss function w.r.t. f
 */
void CNoveltyLoss::LossAndGrad(double& loss, TheMatrix& f, TheMatrix& l)
{
   double* f_array = f.Data();  // pointer to memory location of f (faster element access)
   int len = f.Length();
   l.Zero();  // grad := l'*X
   
   for(int i=0; i < len; i++) 
   {
      if(rho > f_array[i])
      {
         loss += rho - f_array[i];
         l.Set(i, -1.0);
      }
   }
}
Example #6
0
/**  
 *  Compute hinge loss. CAUTION: f is passed by reference and is
 *  changed within this function. This is done for efficiency reasons,
 *  otherwise we would have had to create a new copy of f. 
 *   
 *  @param loss [write] loss value computed.
 *  @param f [read/write] prediction vector. 
 */
void CLogisticLoss::Loss(double& loss, TheMatrix& f)
{
	loss = 0;
	f.ElementWiseMult(_data->labels());  // f = y*f
	double* f_array = f.Data();  // pointer to memory location of f (faster element access)
	int len = f.Length();
	for(int i=0; i < len; i++)
    {
		if(fabs(f_array[i]) == 0.0)
            loss += LN2;
        else if (f_array[i] > 0.0)
            loss += log(1+exp(-f_array[i]));
        else
            loss += log(1+exp(f_array[i])) - f_array[i];
    }
}
/**  
 *  Compute loss and partial derivative of NDCGRank loss w.r.t f
 *   
 *  @param loss [write] loss value computed.
 *  @param f [r/w] = X*w
 *  @param l [write] partial derivative of loss w.r.t. f
 */
void CNDCGRankLoss::LossAndGrad(Scalar& loss, TheMatrix& f, TheMatrix& l)
{
  // chteo: here we make use of the subset information 
        
  loss = 0.0;	
  l.Zero();  
  Scalar* f_array = f.Data();  
  for(int q=0; q < _data->NumOfSubset(); q++)
    {
      //cout << "q = "<< q <<endl;
      int offset = _data->subset[q].startIndex;
      int subsetsize = _data->subset[q].size;
      current_ideal_pi = sort_vectors[q];
      vector<double> b = bs[q];

      //compute_coefficients(offset, subsetsize, y_array, current_ideal_pi, a, b);
      
      //cout << "before finding permutation\n";
      /* find the best permutation */
      find_permutation(subsetsize, offset, a, b, c, f_array, pi);
      //cout << "after finding permutation\n";

      //cout << "before finding delta\n";
      /* compute the loss */
      double value;
      delta(subsetsize, a, b, pi, value);
      //cout << "before finding delta\n";

      loss += value;
      
      for (int i=0;i<subsetsize;i++){
	loss = loss + c[i]*(get(f_array, offset, pi[i]) - get(f_array, offset, i));
      }
      
      for (int i=0;i<subsetsize;i++){
	//add(l, offset, i, c[pi[i]] - c[i]);
	add(l, offset, i, - c[i]);
	add(l, offset, pi[i], c[i]);
      }
    }
  

}
Example #8
0
void CGenericLoss::ComputeLossAndGradient(double& loss, TheMatrix& grad)
{
  loss = 0;
  grad.Zero();
  TheMatrix &w = _model->GetW();
  double* dat = w.Data();
  double* raw_g = grad.Data();

  {
    double* resy;
    double* resybar;

    map<int,int> ybar;

    resy = new double [data->dim()];
    resybar = new double [data->dim()];

    minimize(data->nodeFeatures, &(data->nodeLabels), data->edgeFeatures, dat, dat + data->nNodeFeatures, ybar, data->nNodeFeatures, data->nEdgeFeatures, data->lossPositive, data->lossNegative, data->indexEdge, NULL, 1, data->firstOrderResponses);

    Phi(data->nodeFeatures, &(data->nodeLabels), data->edgeFeatures, data->nNodeFeatures, data->nEdgeFeatures, resy,    resy    + data->nNodeFeatures, data->indexEdge);
    Phi(data->nodeFeatures, &ybar,               data->edgeFeatures, data->nNodeFeatures, data->nEdgeFeatures, resybar, resybar + data->nNodeFeatures, data->indexEdge);
    
    loss += LabelLoss(data->nodeLabels, ybar, data->lossPositive, data->lossNegative, LOSS);

    for (int j = 0; j < (int) data->dim(); j ++)
    {
      loss += dat[j]*(resybar[j]-resy[j]);
      raw_g[j] += (1.0/data->N)*(resybar[j]-resy[j]);
    }

    delete [] resy;
    delete [] resybar;
  }

  loss = loss/data->N;
}