#Hyperparameter

Science Slamscienceslam
2023-09-21

🧐 Künstlich Intelligent lernen 💻 – Theresa Eimer beschäftigt sich als Informatikerin damit, wie man künstlich intelligent lernen kann. Besonders wichtig dabei: Hyperparameter. Doch wie funktioniert maschinelles Lernen überhaupt?🎓
Hier gehts zum Vortrag: youtu.be/UQ4y5ovvp2Y

New Submissions to TMLRtmlrsub@sigmoid.social
2023-06-08

Sample Average Approximation for Black-Box Variational Inference

openreview.net/forum?id=Lvg10L

#variational #optimization #hyperparameter

Published papers at TMLRtmlrpub@sigmoid.social
2023-02-02

No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL

Han Wang, Archit Sakhadeo, Adam M White et al.

openreview.net/forum?id=AiOUi3

#hyperparameters #hyperparameter #learns

2022-11-29

2/10) #SSL models show great promise and can learn #representations from large-scale unlabelled data. But, identifying the best model across diff #hyperparameter configs requires measuring downstream task performance, which requires #labels and adds to the #compute time+resources. 😕

#AI #ML #deeplearning

2022-11-09

I wonder if anyone has written about #ASHA #hyperparameter optimization vs restart strategies.

I've been playing around with ASHA in #ray on my CMA-ES optimization task. Turns out my hyperparameters (population_size, sigma_0) are almost uncorrelated to performance, but the final performance varies a lot per run.

So what ASHA actually does for me is just picking the lucky runs. Which helped a lot. Maybe I should try this BIPOP restarting strategy of CMA-ES instead.

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst