Search algorithms for zero-shot NAS
Open
- Dominant language
- Python
- Stars
- 595
- Forks
- 133
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
Are there any plans to add and make a centralized api for differed zeroshot searching algorithms?
For example, "random search" from NAs w/o training paper; "prune-based search" from TE-NAS paper; "genetic search" from Zen-NAS; "reinforce" and etc.
Contributor guide
Research direction
The issue does not name specific files, tests, or entry points. Start by reviewing how NASLib currently represents search spaces and optimizers, then clarify the desired centralized interface and supported algorithms, including random, prune-based, genetic, and reinforcement search. Done would mean an agreed API and implementation scope for the requested zero-shot search methods.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100