You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When the initial x in the Rosenbrock example is changed from zeros to random, the linesearch fails.
VectorXf x = VectorXf::Random(n);
The linesearch fails the sufficient decrease condition.
I ran into this trying to use this BFGS optimizer on a neural net. Reproduced it with the included Rosenbrock example. I haven't figured out the problem, but was wondering if you know.
The text was updated successfully, but these errors were encountered:
When the initial x in the Rosenbrock example is changed from zeros to random, the linesearch fails.
VectorXf x = VectorXf::Random(n);
The linesearch fails the sufficient decrease condition.
I ran into this trying to use this BFGS optimizer on a neural net. Reproduced it with the included Rosenbrock example. I haven't figured out the problem, but was wondering if you know.
The text was updated successfully, but these errors were encountered: