callous-youth/BOAT

Health v2 · maintenance only

Adoption not part of the score

1143 stars · 159 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

BOAT is a PyTorch-based library providing a compositional, operation-level toolbox for gradient-based bi-level optimization (BLO). It decomposes BLO workflows into 19 atomic gradient operations that can be automatically composed into over 85 solver variants.

Use cases

• implement bi-level optimization algorithms in PyTorch
• compose custom gradient-based BLO solvers from atomic operations
• run meta-learning experiments with bi-level optimization
• solve hyperparameter optimization via gradient-based BLO
• compare different bi-level optimization solver variants
• prototype new bi-level optimization methods without writing solvers from scratch

When to choose

• you need flexible, composable bi-level optimization primitives rather than fixed solver routines
• you work in PyTorch and want a research-oriented BLO framework with many solver variants
• you want to experiment with or extend gradient-based bi-level optimization algorithms

When to avoid

• you need a simple hyperparameter tuning tool rather than a research BLO framework
• your project does not use PyTorch or one of the supported alternative backends (Jittor, MindSpore)
• you need production-ready, turnkey AutoML rather than low-level optimization building blocks

Facets

library · maturity active

machine-learning sdk developer-tools machine-learning deep-learning python cross-platform bi-level-optimization pytorch hyperparameter-optimization meta-learning gradient-based-optimization compositional-operations optimization algorithms research

Member repositories

For agents

markdown · JSON · MCP: product_card(name="callous-youth/BOAT")