diff options
| author | GaetanMarceauCaron <gaetan.marceau-caron@inria.fr> | 2016-04-15 17:28:29 +0300 |
|---|---|---|
| committer | GaetanMarceauCaron <gaetan.marceau-caron@inria.fr> | 2016-04-15 17:28:29 +0300 |
| commit | f9cd545edb06bede2a3f5b98987a65fcad777c81 (patch) | |
| tree | 989a74232fae89d165840dc562b86bf7c15aa37b | |
| parent | 3eb226834d822191027b914c366757fa81c8fcbe (diff) | |
small modif
| -rw-r--r-- | README.md | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -235,6 +235,7 @@ As always, the step-size must be chosen accordingly. Two additional arguments are also possible: * gamma (default=0.01): determine the update rate of the metric for a minibatch setting, i.e., (1-gamma) * oldMetric + gamma newMetric. Smaller minibatches require a smaller gamma. A default value depending on the size of the minibatches is `gamma = 1. - torch.pow(1.-1./nTraining,miniBatchSize)` where `nTraining` is the number of training examples of the dataset and `miniBatchSize` is the number of training examples per minibatch. * qdFlag (default=true): Whether to use the quasi-diagonal reduction (true) or only the diagonal (false). The former should be better. + This module is a straightforward implementation of the outer product gradient descent. ## Requirements |