Research map / Learning theory and algorithms / Combinatorial and search optimization
LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
Kensen Shi, Hanjun Dai, Wen-Ding Li, Kevin Ellis, Charles Sutton
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use LambdaBeam with random restarts instead of λ² | program synthesis search · Handwritten evaluation tasks | tasks solved: 24% more tasks | Improved |
| add random restarts (ablation) | LambdaBeam · Handwritten evaluation tasks | tasks solved | Improved |
| add random restarts (ablation) | LambdaBeam · Synthetic evaluation tasks | tasks solved | Improved |
| Use LambdaBeam with random restarts rather than other compared approaches | program synthesis search · Synthetic evaluation tasks | tasks solved | Improved |
| Use LambdaBeam with random restarts rather than other neural approaches | program synthesis search · Handwritten evaluation tasks | true positive solutions: nearly 8 tasks | Improved |
| Use LambdaBeam rather than Enumeration | program synthesis search · Synthetic evaluation tasks | true positive solutions | Mixed |
Closest papers by meaning
- CrossBeam: Learning to Search in Bottom-Up Program Synthesis (ICLR 2022 · similarity 0.91)
- Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages (NeurIPS 2021 · similarity 0.88)
- Eco Search: A No-delay Best-First Search Algorithm for Program Synthesis (AAAI 2025 · similarity 0.87)
- HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis (NeurIPS 2024 · similarity 0.85)
- Program Synthesis with Best-First Bottom-Up Search (Abstract Reprint) (AAAI 2024 · similarity 0.85)
- Searching Latent Program Spaces (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
