# RASP-QAOA: Resource-Aware Per-Instance Selection for Exact QAOA Simulation

arXiv: https://arxiv.org/abs/2608.05646 · HTML: https://mlsanity.com/paper/2608.05646/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [Automated Algorithm Selection: Survey and Perspectives](https://mlsanity.com/paper/1811.11597/) (2018)
- [Learning to Optimize Variational Quantum Circuits to Solve Combinatorial Problems](https://mlsanity.com/paper/1911.11071/) (2019)
- [cuQuantum SDK: A High-Performance Library for Accelerating Quantum Science](https://mlsanity.com/paper/2308.01999/) (2023)
- [Online Planner Selection with Graph Neural Networks and Adaptive Scheduling](https://mlsanity.com/paper/1811.00210/) (2018)
- [Automatic Construction of Parallel Portfolios via Explicit Instance Grouping](https://mlsanity.com/paper/1804.06088/) (2018)
- [Fast Simulation of High-Depth QAOA Circuits](https://mlsanity.com/paper/2309.04841/) (2023)
- [Machine Learning for Online Algorithm Selection under Censored Feedback](https://mlsanity.com/paper/2109.06234/) (2021)
- [GPU-Accelerated Quantum Simulation: Empirical Backend Selection, Gate Fusion, and Adaptive Precision](https://mlsanity.com/paper/2604.03816/) (2026)
- [Maestro: Intelligent Execution for Quantum Circuit Simulation](https://mlsanity.com/paper/2512.04216/) (2025)

## Abstract (arXiv)

Exact QAOA simulation spans several computational representations whose useful regions differ sharply across graph structure, circuit depth, precision, and available memory. Choosing only a backend name hides these differences: an executable choice also fixes the representation, adapter, precision mode, and memory policy. We introduce RASP-QAOA, a per-instance selector over ten such actions. It first removes actions that cannot implement the requested QAOA semantics or execution requirements, then orders the remaining actions using instance features; actions outside learned support are handled by analytical work estimates. On a content-disjoint 60-request H200 evaluation, RASP-QAOA succeeds on all 31 requests for which at least one admissible action completes and validates. Within this set it reaches 27/31 top-1 and 31/31 top-2 selection, with 1.051 geometric-mean regret. Its failure-penalized PAR10 score is 0.0396 times that of development-selected CUAOA (95% interval: 0.0085-0.1644). A separate 30-request crossover shows that graph structure changes 16 decisions and improves the paired penalized score, while a depth-1 stump matches gradient boosting. The evidence supports resource-aware representation selection at n <= 35, p <= 5, with gains driven by representation features rather than classifier complexity.