Source: lua-torch-optim
Section: interpreters
Priority: optional
Maintainer: Debian Science Maintainers <debian-science-maintainers@lists.alioth.debian.org>
Uploaders: Mo Zhou <cdluminate@gmail.com>
Build-Depends: debhelper (>=11),
               dh-lua,
# lua-torch-torch7 is not a real B-D, but an explicit runtime dependency
               lua-torch-torch7,
Standards-Version: 4.1.4
Homepage: https://github.com/torch/optim
Vcs-Browser: https://salsa.debian.org/science-team/lua-torch-optim
Vcs-Git: https://salsa.debian.org/science-team/lua-torch-optim.git

Package: lua-torch-optim
Architecture: all
Multi-Arch: foreign
Depends: ${misc:Depends},
         lua5.1 | luajit,
         lua-torch-torch7,
         lua-torch-xlua,
XB-Lua-Versions: ${lua:Versions}
Description: Numeric Optimization Package for Torch Framework
 This package contains several optimization routines and a logger for Torch.
 .
 The following algorithms are provided:
  * Stochastic Gradient Descent
  * Averaged Stochastic Gradient Descent
  * L-BFGS
  * Congugate Gradients
  * AdaDelta
  * AdaGrad
  * Adam
  * AdaMax
  * FISTA with backtracking line search
  * Nesterov's Accelerated Gradient method
  * RMSprop
  * Rprop
  * CMAES
 All these algorithms are designed to support batch optimization as well
 as stochastic optimization. It's up to the user to construct an objective
 function that represents the batch, mini-batch, or single sample on which
 to evaluate the objective.
 .
 This package provides also logging and live plotting capabilities via the
 `optim.Logger()` function. Live logging is essential to monitor the
 network accuracy and cost function during training and testing, for
 spotting under- and over-fitting, for early stopping or just for monitoring
 the health of the current optimisation task.