Hybrid LLM and Higher-Order Quantum Approximate Optimization for CSA Collateral Management
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918178886516736 |
|---|---|
| author | Jin, Tao Florescu, Stuart Heyu Jin |
| author_facet | Jin, Tao Florescu, Stuart Heyu Jin |
| contents | We address finance-native collateral optimization under ISDA Credit Support Annexes (CSAs), where integer lots, Schedule A haircuts, RA/MTA gating, and issuer/currency/class caps create rugged, legally bounded search spaces. We introduce a certifiable hybrid pipeline purpose-built for this domain: (i) an evidence-gated LLM that extracts CSA terms to a normalized JSON (abstain-by-default, span-cited); (ii) a quantum-inspired explorer that interleaves simulated annealing with micro higher order QAOA (HO-QAOA) on binding sub-QUBOs (subset size n <= 16, order k <= 4) to coordinate multi-asset moves across caps and RA-induced discreteness; (iii) a weighted risk-aware objective (Movement, CVaR, funding-priced overshoot) with an explicit coverage window U <= Reff+B; and (iv) CP-SAT as single arbiter to certify feasibility and gaps, including a U-cap pre-check that reports the minimal feasible buffer B*. Encoding caps/rounding as higher-order terms lets HO-QAOA target the domain couplings that defeat local swaps. On government bond datasets and multi-CSA inputs, the hybrid improves a strong classical baseline (BL-3) by 9.1%, 9.6%, and 10.7% across representative harnesses, delivering better cost-movement-tail frontiers under governance settings. We release governance grade artifacts-span citations, valuation matrix audit, weight provenance, QUBO manifests, and CP-SAT traces-to make results auditable and reproducible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26217 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid LLM and Higher-Order Quantum Approximate Optimization for CSA Collateral Management Jin, Tao Florescu, Stuart Heyu Jin Computational Finance Artificial Intelligence Optimization and Control 90C10, 90C27 (Primary), 90C59, 68Q12, 68T50, 91G80, 91G60 (Secondary) I.2.7; I.2.6; G.1.6; F.1.2; G.2.1; J.1 We address finance-native collateral optimization under ISDA Credit Support Annexes (CSAs), where integer lots, Schedule A haircuts, RA/MTA gating, and issuer/currency/class caps create rugged, legally bounded search spaces. We introduce a certifiable hybrid pipeline purpose-built for this domain: (i) an evidence-gated LLM that extracts CSA terms to a normalized JSON (abstain-by-default, span-cited); (ii) a quantum-inspired explorer that interleaves simulated annealing with micro higher order QAOA (HO-QAOA) on binding sub-QUBOs (subset size n <= 16, order k <= 4) to coordinate multi-asset moves across caps and RA-induced discreteness; (iii) a weighted risk-aware objective (Movement, CVaR, funding-priced overshoot) with an explicit coverage window U <= Reff+B; and (iv) CP-SAT as single arbiter to certify feasibility and gaps, including a U-cap pre-check that reports the minimal feasible buffer B*. Encoding caps/rounding as higher-order terms lets HO-QAOA target the domain couplings that defeat local swaps. On government bond datasets and multi-CSA inputs, the hybrid improves a strong classical baseline (BL-3) by 9.1%, 9.6%, and 10.7% across representative harnesses, delivering better cost-movement-tail frontiers under governance settings. We release governance grade artifacts-span citations, valuation matrix audit, weight provenance, QUBO manifests, and CP-SAT traces-to make results auditable and reproducible. |
| title | Hybrid LLM and Higher-Order Quantum Approximate Optimization for CSA Collateral Management |
| topic | Computational Finance Artificial Intelligence Optimization and Control 90C10, 90C27 (Primary), 90C59, 68Q12, 68T50, 91G80, 91G60 (Secondary) I.2.7; I.2.6; G.1.6; F.1.2; G.2.1; J.1 |
| url | https://arxiv.org/abs/2510.26217 |