ENH add MI simulations #199
Conversation
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## main #199 +/- ##
==========================================
- Coverage 90.18% 88.85% -1.33%
==========================================
Files 49 49
Lines 4198 4335 +137
==========================================
+ Hits 3786 3852 +66
- Misses 412 483 +71 ☔ View full report in Codecov by Sentry. |
Signed-off-by: Adam Li <adam2392@gmail.com>
Signed-off-by: Adam Li <adam2392@gmail.com>
Signed-off-by: Adam Li <adam2392@gmail.com>
Signed-off-by: Adam Li <adam2392@gmail.com>
Signed-off-by: Adam Li <adam2392@gmail.com>
|
@adam2392 |
|
Good point. Wanna add that and an error check on the value of mix being in (0,1) there? |
Signed-off-by: Adam Li <adam2392@gmail.com>
| """ | ||
| rng = np.random.default_rng(seed=seed) | ||
|
|
||
| mu_1 = np.array([1 / np.sqrt(i) for i in range(1, n_dim + 1)]) |
There was a problem hiding this comment.
Aren't these mu's reversed from what we defined on board? F should be mu and G should be -mu. @sampan501 @adam2392
There was a problem hiding this comment.
I think it should be fine since it is symmetrical.
There was a problem hiding this comment.
I don't think we should add extra confusion in it.
There was a problem hiding this comment.
I personally don't feel strongly either way
Signed-off-by: Adam Li <adam2392@gmail.com>
Signed-off-by: Adam Li <adam2392@gmail.com>
|
Thanks @PSSF23 and @sampan501 ! Putting this in, so we can move towards some of the other tasks If the mu0 vs mu1 ends up being confusing, feel free to propose the change in another PR. |
Add simulations that use conditional entropy to calculate MI