Neeratyoy Mallik

* Added option to record Learning Curves * _Bug fix_: new tabular data collected by training on train set and evaluating on validation set

Allow for freeze-thaw of configurations where possible

3

To allow for a wider multi-fidelity scope, it would be nice to allow configurations to be optionally restarted from a model checkpoint. This would be applicable for the tree-based search...

Adding public URLs for tabular benchmark

3

Added the figshare public URLs. Couldn't successfully test it though. Tried the following: ```python from hpobench.benchmarks.ml_mmfb import TabularBenchmark benchmark = TabularBenchmark(data_dir=None, model="svm", task_id=10101) ``` Failed with the error `TypeError: int()...

Need to create unit tests to check all combination of input-output pairs of data type conversions allowed in openml-python. For example: ARFF -> DENSE ARFF -> SciPy Sparse matirx Sparse...

Redoing #157.

Check restarting/handling of pending config when resuming a run

3

For potential reproducibility of the observed issue: * Running Random Search for 20 (`max_evaluations_total`) evaluations distributed across 4 workers * Midway through the run, killed a worker and restarted the...

Improve readability of DEHB examples and docstrings

1

It will be useful to have more elaborate _filler_ text in the notebooks serving as [examples](https://github.com/automl/DEHB/tree/master/examples) for using DEHB. Also, it will be useful to have more docstrings that help...

The diffs will contain either suggested changes or TODOs meant as requested changes. Let this PR remain active for some time as I go through different sections of the repo.