Comments (1)
This issue is mainly related to supervised learning where a dataset is needed. Because the optimizee is stateless an easy access to certain data in the dataset is not possible from within the optimizee. Right now, the data has to be supplied by the stateful optimizer. But this is a problem for the optimzer as well since it isn't general anymore. That is where an independent structure is useful. It would allow to be accessible both to the optimizer and optimizee. The optimizer could takeover the handling of the dataset without really knowing it's contents. E.g. it would index the dataset in a standardized manner and send the index to the optimizee as well. In general this is similar to a model view controller design.
from l2l.
Related Issues (20)
- Load trajectory with the right parameters for each optimizee
- Revision of the log_stdout flag
- Feature Request: Clean restarts
- Improve the debug functionality HOT 2
- Enable coverage
- Homogenize the interface of the optimizee towards the bounding function. HOT 1
- Set generation number from trajectory in the optimzier
- srun error when running l2l HOT 3
- Template scheduler is outdated
- Add parameters to the trajectory
- Keep track of the individuals in the Hall of Fame HOT 1
- Standardize Optimizers
- Enhance the access to datasets for supervised training
- Enhance - benchmark the execution of the Optimizer
- Make L2L pip installable
- Enable data exchange between Individuals
- Stop execution when finding errors
- Add checkpointing capabilities to L2L
- Optimizer tests fail after first run
- Add a new ooptimizee for testing
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 l2l.