diff options
author | Clement Farabet <clement.farabet@gmail.com> | 2012-01-22 04:27:45 +0400 |
---|---|---|
committer | Clement Farabet <clement.farabet@gmail.com> | 2012-01-22 04:27:45 +0400 |
commit | 8614d4f89d53345dc9b4f4038c18d104e041b77c (patch) | |
tree | fbc8670cad24158d70e3390ca82268f30661c267 /README.md | |
parent | f5d451b39a70e44896ba691e7455d4030d99e788 (diff) |
fixed README layout
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 12 |
1 files changed, 6 insertions, 6 deletions
@@ -18,9 +18,9 @@ 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) +* 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) |