RegimeNAS: Regime-Aware Differentiable Architecture Search With Theoretical Guarantees for Financial Trading

TL;DR

RegimeNAS is a novel differentiable architecture search framework that explicitly incorporates market regime awareness and theoretical guarantees to improve cryptocurrency trading models, achieving superior accuracy and faster convergence.

Contribution

It introduces a Bayesian search space with convergence guarantees, regime-specific neural modules, and a multi-objective loss function tailored for financial markets.

Findings

Achieves 80.3% MAE reduction over traditional baselines

Converges significantly faster (9 vs. 50+ epochs)

Regime-aware modules improve model robustness

Abstract

We introduce RegimeNAS, a novel differentiable architecture search framework specifically designed to enhance cryptocurrency trading performance by explicitly integrating market regime awareness. Addressing the limitations of static deep learning models in highly dynamic financial environments, RegimeNAS features three core innovations: (1) a theoretically grounded Bayesian search space optimizing architectures with provable convergence properties; (2) specialized, dynamically activated neural modules (Volatility, Trend, and Range blocks) tailored for distinct market conditions; and (3) a multi-objective loss function incorporating market-specific penalties (e.g., volatility matching, transition smoothness) alongside mathematically enforced Lipschitz stability constraints. Regime identification leverages multi-head attention across multiple timeframes for improved accuracy and uncertainty estimation. Rigorous empirical evaluation on extensive real-world cryptocurrency data demonstrates that RegimeNAS significantly outperforms state-of-the-art benchmarks, achieving an 80.3% Mean Absolute Error reduction compared to the best traditional recurrent baseline and converging substantially faster (9 vs. 50+ epochs). Ablation studies and regime-specific analysis confirm the critical contribution of each component, particularly the regime-aware adaptation mechanism. This work underscores the imperative of embedding domain-specific knowledge, such as market regimes, directly within the NAS process to develop robust and adaptive models for challenging financial applications.