Comments (7)
Hi there, taking a look!
from ax.
Is there any particular reason that the developer API is required for your use-case, or can you work around this issue by using the service API instead?
Additionally, if I do not put the data argument (and naively expect that the experiment containing the data will be enough) i get the following error:
DataRequiredError:StandardizeY
transform requires non-empty data.
This is because your the BO model has no prior data off of which to train. Usually, GenerationStrategies begin with a Sobol (random initialization) step, followed by a BO step. The former seeds the search space with data off of which the latter trains. When you provide prior data, it's possible to skip the Sobol step as you saw above, but when no prior data is provided, a Sobol step is required. Does that answer your questions?
from ax.
Understood the latter part! thanks for explaining it
But I do need to use the Developer API, as to generate new samples I'm using the FixedParameters like:
generator_run = model_bridge_with_GPEI.gen(n=N,
fixed_features=ObservationFeatures({
'Parameter1':12345,
'Parameter2':6789
}
) )
Which is not available in the Service API, there's a Feature Request about this somewhere.
from ax.
Hi @Jgmedina95 -- let me find the associated feature request and mark another interest for you. Also re: your comment about not sure why runner is needed -- your guess is right! Essentially a runner defines how to deploy the experiment, meaning how to evaluate the trials and then stores that data somewhere. It also keeps track of where that data is stored so that it can be easily fetched in the future. This page has a bit of info on runners.
Bernie's call-out re: the SOBOL initialization step being missing causing the error seems accurate to me -- does this help answer your question, or would you like further support? Will agree definitely a bit ambiguous, so will also make a note of that.
from ax.
Related Issues (20)
- Setting up robust optimization experiment with MVaR gives error HOT 8
- evaluate_acquisition_function does not work correctly HOT 4
- FullyBayesianMOO memory usage HOT 5
- Example (tutorial) for ST_MTGP_NEHVI HOT 2
- Out of Memory crash issue HOT 6
- "Hyperparameter Optimization via Raytune" link in website is broken. HOT 2
- Using `evaluate_acquisition_function` on `AxClient` causes subsequent optimziation errors HOT 2
- Question : modifications of compute_posterior_pareto_frontier HOT 2
- Tracking of auxiliary metrics HOT 2
- `qMaxValueEntropy` doesn't seem to work with `ObjectiveProperties(minimize=True)` HOT 4
- when should we end the Bandit Optimization HOT 4
- Nontrivial parameter constraints HOT 2
- Can't control arguments in fit_gpytorch_mll under the hood. Getting ABNORMAL_TERMINATION_IN_LNSRCH warning HOT 1
- `_random_seed` not retained when using `ax_client.save_to_json_file()` and `AxClient.load_from_json_file()` HOT 2
- Question: SEBO optimization with parameter dependency | logistic parameter constrains HOT 4
- Tutorial Request: Deploying Runners on Clusters, Debugging Runners/Schedulers HOT 4
- Issue with tolerance for floating point and its relevance when using log_scale = True HOT 7
- Question: does Ax support working with Tensorflow models? HOT 2
- Feature Request: Conditional Parameter Constraints HOT 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 ax.