Comments (3)
For the AHR-ES method, it means the "step-size reduction" has reached below 0.001 than the original one. Currently, there's no optimal stopping criteria, the 0.001 is totally arbitrary and may be to harsh for some models and not enough for others. A recommended approach can be to manually check the convergency and restart with a lower control$convergence if necessary.
from calibrar.
from calibrar.
I just released in CRAN the version 0.9 of the package. This includes a more standard automatic stopping criteria for the AHR-ES method:
- 0: maxit/maxgen only
- 1: 1 OR max step reduction
- 2: relative tolerance on value (smoothing for AHR-ES)
- 3: maximum number of generations without improvement of
reltol
.
The previous method was number 1, and the new default is method 2. It will smooth the history of the objective value (due to the inherent randomness of the method) and after that will apply the same criteria used in derivative based methods (if the difference between iterations/generations is below the relative tolerance, the algorithm stops).
You can check the .smooth_stop2()
function for more details, but the key part is:
x_tol = reltol * (abs(x0) + reltol) # x0 is the current value of the objective function
test = abs(dx) < x_tol # dx is the difference in value of the objective function between generations
from calibrar.
Related Issues (5)
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 calibrar.