sqpe.devContribute
← Back to research
2026 / Optimization

Larch

Larch: Learned Query Optimization for Semantic Predicates

What it contributes

Learns per-row evaluation orders for semantic predicates, using either a sequential decision policy or predicted selectivities.

How to read the evidence

The reported reductions concern tested workloads and baselines; training and runtime overhead should be considered in new deployments.

We checked the primary publication record and abstract. This profile summarizes author-reported work; it does not claim a full-paper audit, implementation audit, or independent reproduction.

Explore the connections

FiltersLearned optimizationSelectivity