Bogdan Budescu
Bogdan Budescu
Has anyone tried using the weights in the original pytorch repo with this code?
How would you be able to use `nptyping` to define the type of a structured array with the following `dtype`: ```python dtype = numpy.dtype([('index', numpy.uint64), ('measurements', numpy.float64, (2,))]) ``` I...
Modifications so that python code runs on windows 64 bit. spearmint_sync braninpy seems to work. Didn't test on linux.
[setup.py](https://github.com/bbudescu/FLAML/blob/c48babd02fa9b3252cf49100599fb99c70794591/setup.py#L66) specifies that the required version of Optuna to be 2.8.0. However, according to `ray` docs (check out the second warning on [this](https://docs.ray.io/en/latest/tune/api/doc/ray.tune.search.optuna.OptunaSearch.html) page) : >Please note that with Optuna...
FLAML offers `metric_constraints`, which are supposed to guide the optimizer towards narrowing (as much as possible) the search space to a region specified by the user. [Here](https://github.com/microsoft/FLAML/blob/c48babd02fa9b3252cf49100599fb99c70794591/flaml/tune/searcher/blendsearch.py#L418) appears to be...
by implementing regular control flow without relying on exception semantics ## Why are these changes needed? The code of the user defined function the parameters of which FLAML is being...
The [initializer](https://github.com/microsoft/FLAML/blob/c48babd02fa9b3252cf49100599fb99c70794591/flaml/tune/searcher/blendsearch.py#L62) of the `BlendSearch` class takes a `cost_attr` parameter that allows the user to specify which one of the reported metrics to consider to be the cost when running...
As I can read in the [docs](https://microsoft.github.io/FLAML/docs/Use-Cases/Tune-User-Defined-Function/#config_constraints-vs-metric_constraints), when passing a valid argument for the `config_constraints` parameter of `flaml.tune.run`, if a particular hyperparameter configuration violates any of the constraints imposed, its...
Is it possible to incrementally (i.e., over multiple runs) add datasets and have SMAC3 find the optimum on the current dataset taking into account trial results from previous optimization sessions...
Can one specify a conditional/hierarchical search space to HEBO? I.e., something similar to [SMAC3](https://automl.github.io/ConfigSpace/main/guide.html#nd-example-categorical-hyperparameters-and-conditions)? E.g., only sample the number of convoutional filters in the second layer of a neural net...