mlsanityData to 14 Oct 2026

Multi-Agent Regime-Conditioned Diffusion (MARCD) for CVaR-Constrained Portfolio Decisions

arXiv 2510.10807 ↗First posted 12 Oct 2025cs.LG q-fin.CPcited by 0

Not on the map. Why?

Abstract (arXiv)

We examine whether regime-conditioned generative scenarios combined with a convex CVaR allocator improve portfolio decisions under regime shifts. We present MARCD, a generative-to-decision framework with: (i) a Gaussian HMM to infer latent regimes; (ii) a diffusion generator that produces regime-conditioned scenarios; (iii) signal extraction via blended, shrunk moments; and (iv) a governed CVaR epigraph quadratic program. Contributions: Within the Scenario stage we introduce a tail-weighted diffusion objective that up-weights low-quantile outcomes relevant for drawdowns and a regime-expert (MoE) denoiser whose gate increases with crisis posteriors; both are evaluated end-to-end through the allocator. Under strict walk-forward on liquid multi-asset ETFs (2005-2025), MARCD exhibits stronger scenario calibration and materially smaller drawdowns: MaxDD 9.3% versus 14.1% for BL (a 34% reduction) over 2020-2025 out-of-sample. The framework provides an auditable pipeline with explicit budget, box, and turnover constraints, demonstrating the value of decision-aware generative modeling in finance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 20 references that are in the map. First posted on arXiv 12 Oct 2025.

Builds on

7 of 20 references.

References · 7

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  3. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  4. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  5. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  6. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 142
  7. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 88

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Factor-Based Conditional Diffusion Model for Contextual Portfolio Optimization
  2. 2026Portfolio Reinforcement Learning with Scenario-Context Rollout
  3. 2026Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
  4. 2025Multi-period Asset-liability Management with Reinforcement Learning in a Regime-Switching Market
  5. 2026Constrained Tabular Diffusion for Finance
  6. 2025Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios
  7. 2024Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study
  8. 2026Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training