Comments (5)
I agree with @PABannier on having a hands-on tutorial on adding new datafit.
We can get inspired by the approach we followed to add Poisson or Gamma datafits.
from skglm.
Go for it !
from skglm.
We have https://contrib.scikit-learn.org/skglm/add.html with a link in the header but if you did not find it, we may need to think about a better way to emphasize it. Feel free to update the content itself too, now that we have progressed on solvers and API
from skglm.
I was thinking about a more hands-on tutorial, like adding the Poisson datafit. We start from the formulation of the datafit, and derive all the necessary quantities and questions one would need to ask itself to add the datafit (e.g. is my datafit Lipschitz). A mix between maths and code actually.
from skglm.
Also, I find the raw_grad
and raw_hessian
names confusing. I think we should explain into more details what these two methods do in an example combining maths and code.
from skglm.
Related Issues (20)
- ENH Create a solver dispatcher
- ENH Issue a warning when solution found is null HOT 4
- FEAT Add line search for FISTA solver
- ENH Cache Numba compilation for the user HOT 5
- FEAT Add positivity constraint for `L1` and `L21` penalties HOT 2
- FEAT Add Log-sum penalty
- ENH warn/raiseError in WS solvers if penalty is L05 or L23 for ws_strategy='subdiff' HOT 1
- BUG Raise ValueError when `y < 0` for Poisson datafit
- FEAT Add Cox loss HOT 2
- MNT - Merge ``Lasso`` and ``WeightedLasso`` estimators HOT 5
- Considerable overhead when fitting with ``Lasso``
- FEAT - enable fitting ``Lasso``, ``WeightedLasso``, and ``ElasticNet`` with positivity constraint HOT 2
- FEAT add Pinball loss
- Please add option to GeneralizedLinearEstimator to not have an intercept HOT 2
- ENH add solver in readme example
- ENH add ThreeOperatorSplitting Solver
- How to use the proximal operator of MCPenalty for model optimization? HOT 3
- DOC Objectives docstring do not use math mode HOT 1
- ENH - Numba compilation at import instead of execution time
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from skglm.