Comments (5)
Could the following line be the problem?
MLJLinearModels.jl/src/mlj/classifiers.jl
Line 72 in 55f22b0
from mljlinearmodels.jl.
@tlienart Be great if you can take a look at this.
from mljlinearmodels.jl.
In #124 we discussed a new default for the regularization constant of logistic regression. I think this default hasn't changed everywhere...
from mljlinearmodels.jl.
In #124 we discussed a new default for the regularization constant of logistic regression. I think this default hasn't changed everywhere...
Sorry guys I don't have much time to look into this in details at the moment but this:
MLJLinearModels.jl/src/glr/constructors.jl
Lines 141 to 142 in 7e34598
seems to suggest the lambda
should be fine. In discourse it says that if they use lambda = 1e-6
they get expected results (and in the original example they call the default constructor LogisticClassifier()
which should use the default parameter eps()
). This suggests that maybe they're not using the latest version as by default lambda
should be close to 0?
from mljlinearmodels.jl.
Thanks a lot @jbrea of course it's that line and
MLJLinearModels.jl/src/mlj/classifiers.jl
Line 29 in 55f22b0
from mljlinearmodels.jl.
Related Issues (20)
- Docs for L1+std HOT 1
- `LogisticClassifier` lambda and gamma are easy to confuse HOT 1
- Problems when only one class manifest in the training target HOT 5
- What is the new scale_penalty_with_samples=true doing? HOT 12
- TagBot not working HOT 7
- Ncvreg wrapper HOT 1
- `predict` throws an error for `MultinomialClassifier` on crabs dataset
- Add MLJ compliant doc strings to all models
- Help with documentation review HOT 9
- Test proxgrad with gamma=0 HOT 1
- Add MLJTestInterface tests
- cov-only training for L2Loss HOT 3
- Testing quantreg vs MLJLinearModels HOT 7
- should scale_penalty_with_samples = true be defualt? HOT 4
- Expand docs to include cut and past examples for different Regressors HOT 3
- box (or just positive) constraints on enet OLS HOT 4
- generalized / group lasso HOT 1
- Feature request: Support for tables HOT 3
- Huber breakpoint parameter in quantile form? HOT 2
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 mljlinearmodels.jl.