[Insight-users] BSpline parameters

[Luis Ibanez]

Hi Serena,

Yes, the upper and lower bounds will be the extremes of the values
that EACH component of the deformation vectors at EACH node,
can assume.

Note that due to symmetry you probably will have to set those bounds
to pairs  ( -T, +T ).


For details on the inner working of the LBFGSB optimizer,
please refer to the following emails from the mailing list archives:

http://www.itk.org/pipermail/insight-users/2009-July/031468.html

LBFGSB:

http://www.ece.northwestern.edu/~nocedal/lbfgsb.html<http://www.ece.northwestern.edu/%7Enocedal/lbfgsb.html>

References

   - R. H. Byrd, P. Lu and J. Nocedal. A Limited Memory Algorithm for Bound
   Constrained Optimization<http://www.ece.northwestern.edu/%7Enocedal/PSfiles/limited.ps.gz>,
   (1995), SIAM Journal on Scientific and Statistical Computing , 16, 5, pp.
   1190-1208.
   http://www.ece.northwestern.edu/~nocedal/PSfiles/limited.ps.gz<http://www.ece.northwestern.edu/%7Enocedal/PSfiles/limited.ps.gz>

   - C. Zhu, R. H. Byrd and J. Nocedal. L-BFGS-B: Algorithm 778: L-BFGS-B,
   FORTRAN routines for large scale bound constrained
optimization<http://www.ece.northwestern.edu/%7Enocedal/PSfiles/lbfgsb.ps.gz>(1997),
ACM Transactions on Mathematical Software, Vol 23, Num. 4, pp. 550 -
   560.
   http://www.ece.northwestern.edu/~nocedal/PSfiles/lbfgsb.ps.gz<http://www.ece.northwestern.edu/%7Enocedal/PSfiles/lbfgsb.ps.gz>