Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/torch/optim.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorClement Farabet <clement.farabet@gmail.com>2012-01-22 04:25:38 +0400
committerClement Farabet <clement.farabet@gmail.com>2012-01-22 04:25:38 +0400
commitf5d451b39a70e44896ba691e7455d4030d99e788 (patch)
tree72609488360c66802213a65bbc6d893aaddaddf2 /README.md
parentfc1f65f02a81ed471932b28e741f6158aa75fa6c (diff)
Cleaned up README
Diffstat (limited to 'README.md')
-rw-r--r--README.md26
1 files changed, 26 insertions, 0 deletions
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..0524941
--- /dev/null
+++ b/README.md
@@ -0,0 +1,26 @@
+# optim: an optimization package for Torch7
+
+## Requirements
+
+* Torch7 (github.com/andresy/torch)
+
+## Installation
+
+* Install Torch7 (refer to its own documentation).
+* clone this project into dev directory of Torch7.
+* Rebuild torch, it will include new projects too.
+
+## Info
+
+This package contains several optimization routines for Torch7.
+
+Each optimization algorithm is based on the same interface:
+x*, {f}, ... = optim.method(func, x, state)
+
+with:
+func : a user-defined closure that respects this API: f,df/dx = func(x)
+x : the current parameter vector (a 1d torch tensor)
+state : a table of parameters, and state variables, dependent upon the algorithm
+x* : the new parameter vector that minimizes f, x* = argmin_x f(x)
+{f} : a table of all f values, in the order they've been evaluated
+ (for some simple algorithms, like SGD, #f == 1)