Better formatting for docstrings in REPL

* fixed line-wrap issues
* fixed nested list issues

8 files changed, 72 insertions, 72 deletions

diff --git a/adagrad.lua b/adagrad.lua
index a65279f..b23715c 100644
--- a/adagrad.lua
+++ b/adagrad.lua
@@ -1,17 +1,17 @@
 --[[ ADAGRAD implementation for SGD
 
 ARGS:
-- opfunc : a function that takes a single input (X), the point of 
+- `opfunc` : a function that takes a single input (X), the point of
          evaluation, and returns f(X) and df/dX
-- x      : the initial point
-- state  : a table describing the state of the optimizer; after each
+- `x` : the initial point
+- `state` : a table describing the state of the optimizer; after each
          call the state is modified
-  state.learningRate      : learning rate
-  state.paramVariance     : vector of temporal variances of parameters
+- `state.learningRate` : learning rate
+- `state.paramVariance` : vector of temporal variances of parameters
 
 RETURN:
-- x     : the new x vector
-- f(x)  : the function, evaluated before the update
+- `x` : the new x vector
+- `f(x)` : the function, evaluated before the update
 
 ]]
 function optim.adagrad(opfunc, x, config, state)
diff --git a/asgd.lua b/asgd.lua
index bb10bdc..659db22 100644
--- a/asgd.lua
+++ b/asgd.lua
@@ -17,10 +17,10 @@ ARGS:
 - `x`      : the initial point
 - `state`  : a table describing the state of the optimizer; after each
          call the state is modified
-  - `state.eta0`              : learning rate
-  - `state.lambda`            : decay term
-  - `state.alpha`             : power for eta update
-  - `state.t0`                : point at which to start averaging
+- `state.eta0`   : learning rate
+- `state.lambda` : decay term
+- `state.alpha`  : power for eta update
+- `state.t0`     : point at which to start averaging
 
 RETURN:
 - `x`     : the new x vector
diff --git a/cg.lua b/cg.lua
index 9eb4385..a03c220 100644
--- a/cg.lua
+++ b/cg.lua
@@ -8,25 +8,25 @@ http://www.gatsby.ucl.ac.uk/~edward/code/minimize/example.html
 
     [x fx c] = minimize([0 0]', 'rosenbrock', -25)
 
-Note that we limit the number of function evaluations only, it seems much more
-important in practical use.
+Note that we limit the number of function evaluations only, it seems much
+more important in practical use.
 
 ARGS:
 
 - `opfunc` : a function that takes a single input, the point of evaluation.
 - `x`      : the initial point
 - `state` : a table of parameters and temporary allocations.
-  - `state.maxEval`     : max number of function evaluations
-  - `state.maxIter`     : max number of iterations
-  - `state.df[0,1,2,3]` : if you pass torch.Tensor they will be used for temp storage
-  - `state.[s,x0]`      : if you pass torch.Tensor they will be used for temp storage
+- `state.maxEval`     : max number of function evaluations
+- `state.maxIter`     : max number of iterations
+- `state.df[0,1,2,3]` : if you pass torch.Tensor they will be used for temp storage
+- `state.[s,x0]`      : if you pass torch.Tensor they will be used for temp storage
 
 RETURN:
 
 - `x*` : the new x vector, at the optimal point
-- `f`  : a table of all function values: 
-     - `f[1]` is the value of the function before any optimization
-     - `f[#f]` is the final fully optimized value, at x*
+- `f`  : a table of all function values where
+     `f[1]` is the value of the function before any optimization and
+     `f[#f]` is the final fully optimized value, at x*
 
 (Koray Kavukcuoglu, 2012)
 --]]
diff --git a/fista.lua b/fista.lua
index e0da401..7fba128 100644
--- a/fista.lua
+++ b/fista.lua
@@ -5,13 +5,13 @@
 - `pl`       : minimizer of intermediate problem Q(x,y)
 - `xinit`    : initial point
 - `params`   : table of parameters (**optional**)
-    - `params.L`       : 1/(step size) for ISTA/FISTA iteration (0.1)
-    - `params.Lstep`   : step size multiplier at each iteration (1.5)
-    - `params.maxiter` : max number of iterations (50)
-    - `params.maxline` : max number of line search iterations per iteration (20)
-    - `params.errthres`: Error thershold for convergence check (1e-4)
-    - `params.doFistaUpdate` : true : use FISTA, false: use ISTA (true)
-    - `params.verbose` : store each iteration solution and print detailed info (false)
+- `params.L`       : 1/(step size) for ISTA/FISTA iteration (0.1)
+- `params.Lstep`   : step size multiplier at each iteration (1.5)
+- `params.maxiter` : max number of iterations (50)
+- `params.maxline` : max number of line search iterations per iteration (20)
+- `params.errthres`: Error thershold for convergence check (1e-4)
+- `params.doFistaUpdate` : true : use FISTA, false: use ISTA (true)
+- `params.verbose` : store each iteration solution and print detailed info (false)
 
 On output, `params` will contain these additional fields that can be reused.
 
@@ -36,7 +36,7 @@ Algorithm is published in
        Title = {A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems},
        Volume = {2},
        Year = {2009}}
---]]
+]]
 function optim.FistaLS(f, g, pl, xinit, params)
    
    local params = params or {}
diff --git a/lbfgs.lua b/lbfgs.lua
index bea9db3..0acef53 100644
--- a/lbfgs.lua
+++ b/lbfgs.lua
@@ -13,22 +13,22 @@ rate allows a reduction of confidence in the step size.
 
 ARGS:
 
-- `opfunc` : a function that takes a single input (X), the point of 
+- `opfunc` : a function that takes a single input (X), the point of
          evaluation, and returns f(X) and df/dX
-- `x`      : the initial point
-- `state`  : a table describing the state of the optimizer; after each
+- `x` : the initial point
+- `state` : a table describing the state of the optimizer; after each
          call the state is modified
-  - `state.maxIter`      :  Maximum number of iterations allowed
-  - `state.maxEval`      :  Maximum number of function evaluations
-  - `state.tolFun`       :  Termination tolerance on the first-order optimality
-  - `state.tolX`         :  Termination tol on progress in terms of func/param changes
-  - `state.lineSearch`   :  A line search function
-  - `state.learningRate` : If no line search provided, then a fixed step size is used
+- `state.maxIter` : Maximum number of iterations allowed
+- `state.maxEval` : Maximum number of function evaluations
+- `state.tolFun` : Termination tolerance on the first-order optimality
+- `state.tolX` : Termination tol on progress in terms of func/param changes
+- `state.lineSearch` : A line search function
+- `state.learningRate` : If no line search provided, then a fixed step size is used
 
 RETURN:
 - `x*` : the new `x` vector, at the optimal point
 - `f`  : a table of all function values: 
-     `f[1]` is the value of the function before any optimization
+     `f[1]` is the value of the function before any optimization and
      `f[#f]` is the final fully optimized value, at `x*`
 
 (Clement Farabet, 2012)
diff --git a/lswolfe.lua b/lswolfe.lua
index fe9b767..d7beb4f 100644
--- a/lswolfe.lua
+++ b/lswolfe.lua
@@ -1,25 +1,24 @@
 --[[ A Line Search satisfying the Wolfe conditions
 
 ARGS:
-- `opfunc` : a function (the objective) that takes a single input (X), 
+- `opfunc` : a function (the objective) that takes a single input (X),
          the point of evaluation, and returns f(X) and df/dX
-- `x`      : initial point / starting location
-- `t`      : initial step size
-- `d`      : descent direction
-- `f`      : initial function value
-- `g`      : gradient at initial location
-- `gtd`    : directional derivative at starting location
-- `options`:
-   - `c1`      : sufficient decrease parameter
-   - `c2`      : curvature parameter
-   - `tolX`    : minimum allowable step length
-   - `maxIter` : maximum nb of iterations
+- `x`          : initial point / starting location
+- `t`          : initial step size
+- `d`          : descent direction
+- `f`          : initial function value
+- `g`          : gradient at initial location
+- `gtd`        : directional derivative at starting location
+- `options.c1` : sufficient decrease parameter
+- `options.c2` : curvature parameter
+- `options.tolX`    : minimum allowable step length
+- `options.maxIter` : maximum nb of iterations
 
 RETURN:
-- `f`      : function value at x+t*d
-- `g`      : gradient value at x+t*d
-- `x`      : the next x (=x+t*d)
-- `t`      : the step length
+- `f`          : function value at x+t*d
+- `g`          : gradient value at x+t*d
+- `x`          : the next x (=x+t*d)
+- `t`          : the step length
 - `lsFuncEval` : the number of function evaluations
 ]]
 function optim.lswolfe(opfunc,x,t,d,f,g,gtd,options)
diff --git a/rprop.lua b/rprop.lua
index 9988aa0..d8abf2d 100644
--- a/rprop.lua
+++ b/rprop.lua
@@ -1,17 +1,17 @@
 --[[ A plain implementation of RPROP
 
 ARGS:
-- `opfunc` : a function that takes a single input (X), the point of 
+- `opfunc` : a function that takes a single input (X), the point of
              evaluation, and returns f(X) and df/dX
 - `x`      : the initial point
 - `state`  : a table describing the state of the optimizer; after each
              call the state is modified
- - `state.stepsize`    : initial step size, common to all components
- - `state.etaplus`     : multiplicative increase factor, > 1 (default 1.2)
- - `state.etaminus`    : multiplicative decrease factor, < 1 (default 0.5)
- - `state.stepsizemax` : maximum stepsize allowed (default 50)
- - `state.stepsizemin` : minimum stepsize allowed (default 1e-6)
- - `state.niter`       : number of iterations (default 1)
+- `state.stepsize`    : initial step size, common to all components
+- `state.etaplus`     : multiplicative increase factor, > 1 (default 1.2)
+- `state.etaminus`    : multiplicative decrease factor, < 1 (default 0.5)
+- `state.stepsizemax` : maximum stepsize allowed (default 50)
+- `state.stepsizemin` : minimum stepsize allowed (default 1e-6)
+- `state.niter`       : number of iterations (default 1)
 
 RETURN:
 - `x`     : the new x vector
diff --git a/sgd.lua b/sgd.lua
index 3f57f7e..9642069 100644
--- a/sgd.lua
+++ b/sgd.lua
@@ -1,23 +1,24 @@
 --[[ A plain implementation of SGD
 
 ARGS:
-- `opfunc` : a function that takes a single input (X), the point of 
-             evaluation, and returns f(X) and df/dX
+
+- `opfunc` : a function that takes a single input (X), the point
+             of a evaluation, and returns f(X) and df/dX
 - `x`      : the initial point
 - `config` : a table with configuration parameters for the optimizer
-  - `config.learningRate`      : learning rate
-  - `config.learningRateDecay` : learning rate decay
-  - `config.weightDecay`       : weight decay
-  - `config.momentum`          : momentum
-  - `config.dampening`         : dampening for momentum
-  - `config.nesterov`          : enables Nesterov momentum
+- `config.learningRate`      : learning rate
+- `config.learningRateDecay` : learning rate decay
+- `config.weightDecay`       : weight decay
+- `config.momentum`          : momentum
+- `config.dampening`         : dampening for momentum
+- `config.nesterov`          : enables Nesterov momentum
 - `state`  : a table describing the state of the optimizer; after each
              call the state is modified
-  - `state.learningRates`      : vector of individual learning rates
+- `state.learningRates`      : vector of individual learning rates
 
 RETURN:
-- x     : the new x vector
-- f(x)  : the function, evaluated before the update
+- `x`     : the new x vector
+- `f(x)`  : the function, evaluated before the update
 
 (Clement Farabet, 2012)
 ]]