[mlpack-svn] [MLPACK] #254: NCA does not find good solutions
MLPACK Trac
trac at coffeetalk-1.cc.gatech.edu
Thu Oct 25 15:36:18 EDT 2012
#254: NCA does not find good solutions
---------------------+------------------------------------------------------
Reporter: rcurtin | Owner:
Type: defect | Status: new
Priority: major | Milestone: mlpack 1.0.4
Component: mlpack | Keywords: nca, cgd, solution, convergence, nonconvex
Blocking: | Blocked By:
---------------------+------------------------------------------------------
Currently NCA uses the L-BFGS optimizer, but, the NCA objective function
is potentially nonconvex and thus the L-BFGS optimizer may not find a good
solution.
Here is an excerpt of results comparing a couple of methods:
{{{
cardiotoc train mean train variance runtime (mean)
test mean test variance
baseline 40.423% 0.015178% -----
35.031% 0.065745%
lmnn 71.969% 0.085596% 15.228s
66.050% 0.097625%
nca (mlpack) 38.985% 0.019756% 186.37s
33.103% 0.050762%
nca (matlab)
rca
fdsa
m-h mcmc 66.176% 0.062989% 2892.6s
55.392% 0.10958%
m-h mcmc diag 74.637% 0.036214% 826.43s
66.176% 0.16475%
m-h diag (10k) 77.863% 0.032059% 3005.9s
69.843% 0.07890%
m-h diag (25k) 80.040% 0.018136% 7401.9s
72.038% 0.05013%
gibbs mcmc
}}}
Almost certainly it's getting stuck in local minima. Therefore, we need
to use a different optimizer...
--
Ticket URL: <http://trac.research.cc.gatech.edu/fastlab/ticket/254>
MLPACK <www.fast-lab.org>
MLPACK is an intuitive, fast, and scalable C++ machine learning library developed by the FASTLAB at Georgia Tech under Dr. Alex Gray.
More information about the mlpack-svn
mailing list