search

QB3 / sparse-ho

Fast hyperparameter settings for non-smooth estimators:
http://qb3.github.io/sparse-ho
BSD 3-Clause "New" or "Revised" License
39 stars 15 forks source link

ENH display grad norm in line search + modified example wLasso #70

Closed QB3 closed 3 years ago

QB3 commented 3 years ago

Display gradient norm for the outer optimization problem for the line search

closes #60

QB3 commented 3 years ago

Do you think to other quantities to display @mathurinm ?

codecov-io commented 3 years ago

Codecov Report

Merging #70 (96f47cd) into master (46184d9) will increase coverage by 3.56%. The diff coverage is 0.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master      #70      +/-   ##
==========================================
+ Coverage   67.96%   71.53%   +3.56%     
==========================================
  Files          47       51       +4     
  Lines        3097     3798     +701     
  Branches      278      375      +97     
==========================================
+ Hits         2105     2717     +612     
- Misses        917      989      +72     
- Partials       75       92      +17
Impacted Files Coverage Δ
sparse_ho/optimizers/gradient_descent.py 21.42% <ø> (ø)
sparse_ho/optimizers/line_search.py 65.75% <0.00%> (-4.11%) :arrow_down:
sparse_ho/algo/backward.py 62.79% <0.00%> (-23.88%) :arrow_down:
sparse_ho/tests/test_criterion.py 88.70% <0.00%> (-11.30%) :arrow_down:
sparse_ho/utils_plot.py 0.00% <0.00%> (ø)
sparse_ho/tests/test_grid_search.py 100.00% <0.00%> (ø)
sparse_ho/tests/test_models.py 88.11% <0.00%> (ø)
sparse_ho/tests/test_utils.py 100.00% <0.00%> (ø)
sparse_ho/tests/test_optimizers.py 100.00% <0.00%> (ø)
... and 11 more

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 46184d9...96f47cd. Read the comment docs.

QB3 commented 3 years ago

good for you @agramfort ?