Sarah Segel

Varying configspace index order in PDP and symbolic explanations

1

In the PDP plugin (similar in symbolic expl), the configspace is copied when creating the surrogate model ` surrogate_model = RandomForestSurrogate(run.configspace, seed=0)` and also when creating the PDP ` pdp...

The documentation should be checked and updated. Especially: - For some parts (plugins), documentation is incomplete (shows a "This page is under construction." warning) - API documentation should be updated...

Currently, existing loggers are generally disabled, as enabling them would lead to many unwanted redis-logs. This could be adapted such that only redis-logs are disabled.

Currently, there is no multi-fidelity log for SMACv2, so we might want to add one.

fANOVA: Implement faster version

2

As the current implementation of fANOVA is rather inefficient, we could think about how to make it faster.

The DeepCAVE paper [[Sass et al, 2022] ](https://arxiv.org/pdf/2206.03493.pdf) contains an exemplary study on outlier detection. For a follow-up publication, we might want to add additional studies.

Dependencies: Check and update

2

Not all dependencies are up to date. This needs to be checked and updated.

Plots: Make matplotlib outputs available for more plugins

4

Plots are mainly created with Plotly in DeepCAVE. For some plots, a matplotlib version is available as well. This should be added for more plugins.

Add more tests, especially for: - Run - Converters - Plugins (check API calls) and add correct typing

We could implement some of the ideas presented in [Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems](https://arxiv.org/abs/2111.01584)