experiment-dse

Community

Orchestrate end-to-end design-space exploration for ML experiments.

AuthorShiien
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Design-space exploration for hyperparameters across ML experiments helps researchers discover optimal configurations efficiently.

Core Features & Use Cases

  • Generate a YAML-dicated config list from an experiment plan or parameter ranges.
  • Coordinate batched execution via experiment-run and produce a comprehensive DSE report with best config and sensitivity analysis.
  • Trigger downstream tasks and provide a structured path from experiment-plan to experiment-run.

Quick Start

Start a DSE by supplying an experiment-plan and config.yaml budget, then let the system generate configs.yaml, run batches via experiment-run, and produce a final report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: experiment-dse
Download link: https://github.com/Shiien/Self-Evolved-Research-Framework/archive/main.zip#experiment-dse

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.