PRSVM+, tested

2 files changed, 21 insertions, 28 deletions

diff --git a/main.cpp b/main.cpp
index e89cfe1..eeb6b99 100644
--- a/main.cpp
+++ b/main.cpp
@@ -54,7 +54,7 @@ int predict() {
         rsvm->predict(D,L);
     }
 
-    LOG(INFO)<<"Training finished,saving prediction";
+    LOG(INFO)<<"Finished,saving prediction";
     std::ofstream fout(vm["output"].as<std::string>().c_str());
 
     for (int i=0; i<L.size();++i)
@@ -88,15 +88,6 @@ int main(int argc, char **argv) {
     po::store(po::parse_command_line(argc, argv, desc), vm);
     po::notify(vm);
 
-    /* Conjugate Gradient method test
-    MatrixXd A(3,3);
-    VectorXd b(3),x(3);
-    A<< 1,2,3,2,2,4,3,4,1;
-    b<< 1,1,1;
-    x<< 0,0,0;
-    cg_solve(A,b,x);
-    write_stream(std::cout,x);*/
-
     // Print help if necessary
     if (vm.count("help") || !(vm.count("train") || vm.count("validate") || vm.count("predict"))) {
         std::cout << desc;
diff --git a/model/ranksvmtn.cpp b/model/ranksvmtn.cpp
index fec7935..cd58aa9 100644
--- a/model/ranksvmtn.cpp
+++ b/model/ranksvmtn.cpp
@@ -6,14 +6,17 @@
 using namespace std;
 using namespace Eigen;
 
-const int maxiter = 10;
-const double prec=1e-4;
-const double C=1;
-const double cg_prec=1e-10;
-const double line_prec=1e-10;
-const double line_turb=1e-12;
-
-int cal_Hs(const MatrixXd &D,const vector<int> &rank,const VectorXd &corr,const VectorXd &alpha,const vector<int> &A1,const vector<int> &A2,const double &C,const VectorXd s,VectorXd &Hs)
+const double C=1e-2; // Compensating & scaling
+// Main terminating criteria
+const int maxiter = 10; // max iteration count
+const double prec=1e-4; // precision
+// conjugate gradient
+const double cg_prec=1e-10; // precision
+// line search
+const double line_prec=1e-10; // precision
+const double line_turb=1e-15; // purturbation
+
+int cal_Hs(const MatrixXd &D,const vector<int> &rank,const VectorXd &corr,const VectorXd &alpha,const vector<int> &A1,const vector<int> &A2,const VectorXd s,VectorXd &Hs)
 {
     Hs = VectorXd::Zero(s.rows());
     VectorXd Ds=D*s;
@@ -33,17 +36,17 @@ int cal_Hs(const MatrixXd &D,const vector<int> &rank,const VectorXd &corr,const
             else
                 g+=Ds[rank[j]];
     }
-    Hs = s + (D.transpose()*(alpha.cwiseProduct(Ds) - gamma));
+    Hs = s + C*(D.transpose()*(alpha.cwiseProduct(Ds) - gamma));
     return 0;
 }
 
-int cg_solve(const MatrixXd &D,const vector<int> &rank,const VectorXd &corr,const VectorXd &alph,const vector<int> &A1,const vector<int> &A2,const VectorXd &b,const double &C, VectorXd &x)
+int cg_solve(const MatrixXd &D,const vector<int> &rank,const VectorXd &corr,const VectorXd &alph,const vector<int> &A1,const vector<int> &A2,const VectorXd &b, VectorXd &x)
 {
     double alpha,beta,r_1,r_2;
     int step=0;
     VectorXd q;
     VectorXd Hs;
-    cal_Hs(D,rank,corr,alph,A1,A2,C,x,Hs);
+    cal_Hs(D,rank,corr,alph,A1,A2,x,Hs);
     VectorXd res = b - Hs;
     VectorXd p = res;
     while (1)
@@ -56,7 +59,7 @@ int cg_solve(const MatrixXd &D,const vector<int> &rank,const VectorXd &corr,cons
             beta = r_1 / r_2;
             p = res + p * beta;
         }
-        cal_Hs(D,rank,corr,alph,A1,A2,C,p,q);
+        cal_Hs(D,rank,corr,alph,A1,A2,p,q);
         alpha = r_1/p.dot(q);
         x=x+p*alpha;
         res=res-q*alpha;
@@ -129,7 +132,6 @@ int cal_alpha_beta(const VectorXd &dw,const VectorXd &corr,const vector<int> &A1
 // line search using newton method
 int line_search(const VectorXd &w,const MatrixXd &D,const VectorXd &corr,const vector<int> &A1,const vector<int> &A2,const VectorXd &step,double &t)
 {
-    double wd=w.dot(step),dd=step.dot(step);
     VectorXd Dd = D*step;
     VectorXd Xd = VectorXd::Zero(A1.size());
     VectorXd alpha,beta,yt;
@@ -146,9 +148,9 @@ int line_search(const VectorXd &w,const MatrixXd &D,const VectorXd &corr,const v
         grad=w+t*step;
         Dd = D*(w + t*step);
         cal_alpha_beta(Dd,corr,A1,A2,rank,yt,alpha,beta);
-        grad = grad + (D.transpose()*(alpha.cwiseProduct(yt)-beta));
+        grad = grad + C*(D.transpose()*(alpha.cwiseProduct(yt)-beta));
         g = grad.dot(step);
-        cal_Hs(D,rank,corr,alpha,A1,A2,C,step,Hs);
+        cal_Hs(D,rank,corr,alpha,A1,A2,step,Hs);
         h = Hs.dot(step);
         g=g+line_turb;
         h = h+line_turb;
@@ -186,11 +188,11 @@ int train_orig(int fsize, MatrixXd &D,const vector<int> &A1,const vector<int> &A
         cal_alpha_beta(dw,corr,A1,A2,rank,yt,alpha,beta);
 
         // Generate support vector matrix sv & gradient
-        obj = (weight.dot(weight) + (alpha.dot(yt.cwiseProduct(yt))-beta.dot(yt)))/2;//
-        grad = weight + (D.transpose()*(alpha.cwiseProduct(yt)-beta));
+        obj = (weight.dot(weight) + C*(alpha.dot(yt.cwiseProduct(yt))-beta.dot(yt)))/2;//
+        grad = weight + C*(D.transpose()*(alpha.cwiseProduct(yt)-beta));
         step = grad*0;
         // Solve
-        cg_solve(D,rank,corr,alpha,A1,A2,grad,C,step);
+        cg_solve(D,rank,corr,alpha,A1,A2,grad,step);
         // do line search
         line_search(weight,D,corr,A1,A2,step,t);
         weight=weight+step*t;