/

/

google-research

Обзор Центр заботыВойти

google-research

Ветки: 311 Коммиты: 4490 Теги: 0

..

google-research

/

spaceopt

Making a minimal open-source code release for the paper "Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach" (https://arxiv.org/abs/2112.08250).

3 года назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

branin_comparison.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

gp_utils_test.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

hartman_comparison.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

launch_template_comparison.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

requirements.txt

final staging for the spaceopt code.

3 года назад

run_comparison.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

search_spaces.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

search_spaces_test.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

synthetic_objective_functions.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

README.md

This folder holds code for the following paper: "Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach" (https://arxiv.org/abs/2112.08250), accepted to AISTATS 2022. The paper describes a general method to score and rank the search spaces over which we perform black-box optimization.

Currently, there is code that shows how to score search spaces, but, in order to run it, the user must supply various functions to sample from a GP (or other probabilistic model of the response surface). We plan to release example implementations of the necessary functions in the future.

Использование cookies

Мы используем файлы cookie в соответствии с Политикой конфиденциальности и Политикой использования cookies.

Нажимая кнопку «Принимаю», Вы даете АО «СберТех» согласие на обработку Ваших персональных данных в целях совершенствования нашего веб-сайта и Сервиса GitVerse, а также повышения удобства их использования.

Запретить использование cookies Вы можете самостоятельно в настройках Вашего браузера.