Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
RADAR uses retrieval-augmented diffusion to learn market states for stochastic discount factor portfolio optimization.
The paper introduces RADAR, a retrieval-augmented diffusion framework for portfolio optimization under the stochastic discount factor framework. It learns market-state representations by conditioning on similar historical regimes and builds context-dependent noise distributions rather than assuming isotropic Gaussian noise. Conditional diffusion denoises multimodal price and news inputs, with the process initialized from empirical statistics to reflect state-dependent uncertainty. The authors report state-of-the-art risk-adjusted performance and economically meaningful signals for asset returns and correlations.
- RADAR conditions diffusion on retrieved historical market regimes.
- Context-dependent noise replaces an isotropic Gaussian assumption.
- Conditional diffusion denoises multimodal price and news inputs.
- Authors report stronger risk-adjusted portfolio metrics and return signals.
Full article152 words · extracted from arxiv.org · click to collapse
In this work, we study portfolio optimization under the stochastic discount factor (SDF) framework by learning market state representations that capture the underlying risk structures of financial data. This is challenging due to several factors: financial markets exhibit non-stationary dynamics with shifting regimes, multimodal inputs such as price and news data often contain stochastic noise, and existing diffusion-based approaches, while effective for modeling stochastic dynamics, rely on assumptions such as isotropic Gaussian noise that fail to capture the state-dependent nature of financial uncertainty. To address these challenges, we introduce RADAR, a retrieval-augmented diffusion framework that learns market representations by conditioning on similar historical regimes. RADAR leverages retrieval to construct context-dependent noise distributions, applies conditional diffusion to denoise multimodal representations, and initializes the diffusion process using empirical statistics to reflect state-dependent uncertainty. Experiments show that RADAR achieves state-of-the-art performance on key risk-adjusted metrics while producing economically meaningful signals on asset returns and correlations.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.35086