Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add explanation for the assumption of what counts as signal in BRSA, correct default optimizer of BRSA #337

Merged
merged 47 commits into from Feb 21, 2018

Conversation

lcnature
Copy link
Contributor

add notes in the documentation for the different assumption in BRSA from traditional RSA on what counts as signal. Also corrected the mismatch between documentation and actual implementation of the default optimizer. L-BFGS-B appears to require less memory and fits faster in each iteration than BFGS. But it is possible that more iterations are needed because Hessian is approximated, so the default max number of iteration is increased

lcnature and others added 30 commits September 2, 2016 10:12
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
a
 Changes to be committed:
	new file: brainiak/brsa/test.txt
Please note that the model assumes that the covariance matrix U which
all \\beta_i follow is zero-meaned. For more details of its implication,
see documentation of `.BRSA`

Parameters
----------
n_iter : int. Default: 50
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same.

under the assumption in BRSA, their similarity is 1; under the assumption
that only deviation of pattern from average patterns is signal of interest,
their similarity should be -1.

Parameters
----------
n_iter : int. Default: 50
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This a good example for why we should not list defaults in docstrings: it creates the need to change values in an additional place, which is frequently forgotten, such as in this PR.

My recommendation: do not list the default in the docstring; it is already visible in the HTML docs in the function definition.

@@ -178,7 +178,7 @@ def test_fit():
rank = n_C - 1
n_nureg = 1
brsa = BRSA(rank=rank, n_nureg=n_nureg, tol=2e-3,
n_iter=4, init_iter=4, auto_nuisance=True)
n_iter=20, init_iter=4, auto_nuisance=True)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this the minimum number that works with L-BFGS-B? Just trying to minimize required time for tests.

@mihaic
Copy link
Member

mihaic commented Feb 20, 2018

@lcnature, we are preparing a new release to incorporate PR #339. Will you address the comments (they are really simple) today or tomorrow to get this PR in?

@lcnature
Copy link
Contributor Author

@mihaic Yes! I will resubmit today :)

@mihaic mihaic merged commit 03d83c8 into brainiak:master Feb 21, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants