Problem
Research questions and friction points this paper is trying to address.
Constrained Factor Portfolio Optimization
Photonic Quantum Computing
Mixed-Integer Programming
Deep Reinforcement Learning
Empirical Evaluation
Photonic Quantum Computing vs. Classical Solvers in Constrained Factor Portfolio Optimization
🤖 AI Summary
This study addresses the paradigm selection challenge in institutional factor portfolio optimization by presenting the first rigorous empirical evaluation of photonic quantum annealing, mixed-integer programming, and deep reinforcement learning. The findings reveal that photonic quantum hardware excels in narrow-range optimization, whereas classical programming demonstrates superior robustness under risk control constraints. Conversely, deep reinforcement learning exhibits instability risks associated with higher-order moments. By delineating the advantage boundaries and structural failure modes of each approach, this work bridges a critical gap in cross-paradigm comparison. Ultimately, it provides essential empirical evidence to guide the adaptation and deployment of optimization algorithms within quantitative investment frameworks, offering practitioners a nuanced understanding of algorithmic suitability across different market and constraint regimes.
📝 Abstract
The authors present a rigorous empirical evaluation of three distinct optimization paradigms for institutional factor portfolio construction: an entropy-based photonic quantum annealer (Dirac-3, Quantum Computing Inc.), a commercial mixed-integer programming solver (Gurobi), and a model-free deep reinforcement learning agent (SAC). Evaluating these pipelines on the Jensen-Kelly-Pedersen 13-factor equity library across 164 months test window, we implement a full factorial penalty sweep comprising 48 hyperparameter configurations that govern return, volatility, and skewness trade-offs. Our findings demonstrate that while photonic hardware can locate superior risk-return topologies within a narrow operating range, classical mixed-integer programming remains superior for risk-constrained mandates requiring tight tail-risk control and cross-seed stability. Furthermore, we document structural failure modes in reinforcement learning factor allocators under unanchored higher-moment shaping. We translate these empirical results into actionable, mandate-specific guidelines for quantitative portfolio managers deploying advanced optimization engines.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Photonic Quantum Annealing
Factor Portfolio Optimization
Mixed-Integer Programming
Deep Reinforcement Learning
Empirical Benchmarking
🔎 Similar Papers
No similar papers found.
