himkt

I talked with @hppRC and we decide to free the assignment. If someone is interested in writing a new tutorial, please feel free to comment here!

Thank you for your interest @divyanshugit! The current tutorial show the usage of `optuna create_study` and `optuna study optimize`. But `optuna study optimize` was deprecated in v2.2.0 and Optuna provides...

Hello @KyleKotowick, thank you for opening the issue. And sorry for the late response. ```sh > docker run --rm --platform linux/amd64 -it python:3.9.7 bash root:/usr/local/lib/python3.9/site-packages# pip install optuna ... root:/usr/local/lib/python3.9/site-packages#...

Hi @profPlum, thank you for the feature request! Are you interested in the contribution? It is difficult for us to work on it now since we are now developing the...

Nice! Currently, InMemoryStorage doesn't support multi-process execution. To support multi-process execution with InMemoryStorage, we will need share internal states across processes. For interprocess communication, we can use multiprocessing utilities (the...

I really apologize that I'm inactive for a long time... I think your proposal is related to batch optimization (https://github.com/optuna/optuna/issues/2660), samples multiple configurations at a time and evaluates an objective...

Thank you for the elaboration. I'm not confident I fully understand your idea but let me put another context. > The point is that if you implemented this you could...

> you could use the disk to communicate across nodes Sharing a disk is not a good practice in the setting since we need to control exclusive locking (file locking...

As you mentioned, the help comment says `dev_file` is used to do early stopping. However, current implementation does not seem to stop training loop by watching metrics on dev data....

Hello @hauntsaninja, this is the author of konoha. Thank you so much for the patch of konoha upgrade. (Sorry for being inactive a long time) @alanakbik Now the CI looks...