Jake Robertson

We have included several new parameters for `Bananas` and `Npenas` in order to determine whether the zero cost proxies are used, and whether they come from the benchmark or the...

Extend predictors to zero-cost case

4

In the zerocost branch, `Ensemble` has been extended to the Zero Cost case and contains a single option for its base predictor, `XGBoost`. The `XGBoost` predictor has been adapted to...

Source of validation accuracy in zero-cost case

2

In the zero-cost branch optimizers `Npenas` and `Bananas`, the validation accuracy of architectures is being queried from the zero-cost-benchmark as follows: ```python model.accuracy = self.zc_api[str(model.arch_hash)]['val_accuracy'] ``` The question is, whether...

Storing of models or architectures in optimizers

1

In the `get_candidates` function of the `zerocost` branch optimizers `Bananas` and `Npenas` there is a discrepancy between how candidates in the `next_batch` are stored. If the acquisition function is being...

Finalized Lukas' idea for heat map to visualize the convergence of alpha weights for One-Shot optimizers, via two new configuration parameters `config.save_arch_weights` and `config.plot_arch_weights` Plotting was made to be extensible...

A problem occurs in the `Bananas` optimizer, when an architecture outside of the search space is sampled, and the `zero_cost_scores` must be calculated on-the-fly using the `ZeroCost` ``` Exception has...

issue with fetch_lawschool_gpa

1

Hello, I'm having a problem with downloading the lawschool GPA dataset using the `fetch_lawschool_gpa` function due to an error thrown in `tempeh`'s `seaphe_datasets.py` file. ``` File "/home/robertsj/miniconda3/envs/hpobench_fairmohpo/lib/python3.9/site-packages/tempeh/datasets/seaphe_datasets.py", line 39, in...