We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Below a list of proposed callbacks. Some _end, _begin might be superfluous.
_end
_begin
on_optimization_begin: Additional setup, ....
on_optimization_begin
on_optimization_end: Adapt archive before finishing
on_optimization_end
on_design_eval_start: Add e.g. multiple defaults, meta-learned stuff, ...
on_design_eval_start
on_iteration_begin:
on_iteration_begin
on_iteration_end: Track e.g. loss on held-out dataset || Could be done with mlr3
on_iteration_end
on_acquisition_begin:
on_acquisition_begin
on_acquisition_end: Perform some checks on the proposed points before evaluating.
on_acquisition_end
on_eval_begin:
on_eval_begin
Can I change the AcqFunction hyperparameters depending on some schedule?
AcqFunction
Can I change AcqFunction|Surrogate optimizer after some amount of iterations?
Surrogate
How would I weave in a random eval every nth iteration?
How can I add cheap sub-evals (c.f. classification thresholds, nrounds, ...) into optimization?
Can I terminate optimization if some non-terminator criterion I define e.g. in the acqfun is met?
Can I just debug at a given LOC? i.e. simply adding a callback that calls browser()?
browser()
...
The text was updated successfully, but these errors were encountered:
See also mlr-org/bbotk#180
Sorry, something went wrong.
to the largest extent solved by bbotk callbacks and #152 now
No branches or pull requests
Below a list of proposed callbacks. Some
_end
,_begin
might be superfluous.on_optimization_begin
: Additional setup, ....on_optimization_end
: Adapt archive before finishingon_design_eval_start
: Add e.g. multiple defaults, meta-learned stuff, ...on_iteration_begin
:on_iteration_end
: Track e.g. loss on held-out dataset || Could be done with mlr3on_acquisition_begin
:on_acquisition_end
: Perform some checks on the proposed points before evaluating.on_eval_begin
:Can I change the
AcqFunction
hyperparameters depending on some schedule?Can I change
AcqFunction
|Surrogate
optimizer after some amount of iterations?How would I weave in a random eval every nth iteration?
How can I add cheap sub-evals (c.f. classification thresholds, nrounds, ...) into optimization?
Can I terminate optimization if some non-terminator criterion I define e.g. in the acqfun is met?
Can I just debug at a given LOC? i.e. simply adding a callback that calls
browser()
?...
The text was updated successfully, but these errors were encountered: