arXiv subjects

Yimeng Qiu

Publications and source records attributed to Yimeng Qiu.

5 recordsLinked to original sources

arXiv2026

Representation Homogeneity and Systemic Instability in AI-Dominated Financial Markets: A Structural Approach

This paper investigates how similarity in the informational representation of market states among Artificial Intelligence (AI) trading agents can generate systemic instability in financial markets. We construct a structural multi-agent market model calibrated using high-frequency microstructural moments. AI agents are modeled through a two-layer decision architecture consisting of a nonlinear representation layer and an adaptive linear readout layer. The representation layer maps raw market states into high-dimensional feature vectors, while the readout layer generates return forecasts that feed into a risk-controlled trading rule. This representation-based microfoundation separates two objects that are often conflated in the literature: representation homogeneity (the degree to which agents encode market states into similar feature spaces) and forecast overlap (the degree to which agents produce similar return predictions). We show theoretically that these two concepts are related but not equivalent, and that representation homogeneity can compress the effective space of forecast disagreement under stress even when predictions appear diverse in normal times. Through controlled factorial experiments that vary representation homogeneity while conditioning on alternative risk-aversion and learning-rate distributions, we hypothesize that increasing representation similarity amplifies synchronization in beliefs and positions, leading to volatility clustering, liquidity stress, and elevated tail risk. Our structural mechanisms suggest that low perceived volatility regimes can endogenously accumulate hidden leverage through position stickiness, which subsequently collapses when shocks trigger synchronized deleveraging. The results provide a structural foundation for macroprudential policies aimed at monitoring and preserving diversity in how AI systems represent and process market information.

q-fin.TR↗

arXiv2026

Mislearning of Factor Risk Premia under Structural Breaks: A Misspecified Bayesian Learning Framework

While asset-pricing models increasingly recognize that factor risk premia are subject to structural change, existing literature typically assumes that investors correctly account for such instability. This paper studies how investors instead learn under a misspecified model that underestimates structural breaks. We propose a minimal Bayesian framework in which this misspecification generates persistent prediction errors and pricing distortions, and we introduce an empirically tractable measure of mislearning intensity $(\Delta_t)$ based on predictive likelihood ratios. The empirical results yield three main findings. First, in benchmark factor systems, elevated mislearning does not forecast a deterministic short-run collapse in performance; instead, it is associated with stronger long-horizon returns and Sharpe ratios, consistent with an equilibrium premium for acute model uncertainty. Second, in a broader anomaly universe, this pricing relation does not generalize uniformly: mislearning is more strongly associated with future drawdowns, downside semivolatility, and other measures of instability, with substantial heterogeneity across anomaly families. Third, the cross-sectional relation between instability and mislearning is inherently conditional: while a monotonic link between break-proneness and average mislearning does not hold in the full cross-section, it re-emerges in low-friction (low-IVOL) environments where break-state severity is more comparable across assets.

q-fin.PM↗

arXiv2026

A Three--Dimensional Efficient Surface for Portfolio Optimization

The classical mean-variance framework characterizes portfolio risk solely through return variance and the covariance matrix, implicitly assuming that all relevant sources of risk are captured by second moments. In modern financial markets, however, shocks often propagate through complex networks of interconnections, giving rise to systemic and spillover risks that variance alone does not reflect. This paper develops a unified portfolio optimization framework that incorporates connectedness risk alongside expected return and variance. Using a quadratic measure of network spillovers derived from a connectedness matrix, we formulate a three-objective optimization problem and characterize the resulting three-dimensional efficient surface. We establish existence, uniqueness, and continuity of optimal portfolios under mild regularity conditions and derive closed-form solutions when short-selling is allowed. The trade-off between variance and connectedness is shown to be strictly monotone except in degenerate cases, yielding a well-defined risk-risk frontier. Under simultaneous diagonalizability of the covariance and connectedness matrices, we prove a three-fund separation theorem: all efficient portfolios can be expressed as affine combinations of a minimum-variance portfolio, a minimum-connectedness portfolio, and the tangency portfolio. The framework clarifies how network-based risk alters classical diversification results and provides a transparent theoretical foundation for incorporating systemic connectedness into portfolio choice.

q-fin.PM↗

arXiv2025

Entropy-Guided Multiplicative Updates: KL Projections for Multi-Factor Target Exposures

We introduce Entropy-Guided Multiplicative Updates (EGMU), a convex optimization framework for constructing multi-factor target-exposure portfolios by minimizing Kullback-Leibler divergence from a benchmark under linear factor constraints. We establish feasibility and uniqueness of strictly positive solutions when the benchmark and targets satisfy convex-hull conditions. We derive the dual concave formulation with explicit gradient, Hessian, and sensitivity expressions, and provide two provably convergent solvers: a damped dual Newton method with global convergence and local quadratic rate, and a KL-projection scheme based on iterative proportional fitting and Bregman-Dykstra projections. We further generalize EGMU to handle elastic targets and robust target sets, and introduce a path-following ordinary differential equation for tracing solution trajectories. Stable and scalable implementations are provided using LogSumExp stabilization, covariance regularization, and half-space KL projections. Our focus is on theory and reproducible algorithms; empirical benchmarking is optional.

q-fin.PM↗

arXiv2025

A Multi-Layer Machine Learning and Econometric Pipeline for Forecasting Market Risk: Evidence from Cryptoasset Liquidity Spillovers

We study whether liquidity and volatility proxies of a core set of cryptoassets generate spillovers that forecast market-wide risk. Our empirical framework integrates three statistical layers: (A) interactions between core liquidity and returns, (B) principal-component relations linking liquidity and returns, and (C) volatility-factor projections that capture cross-sectional volatility crowding. The analysis is complemented by vector autoregression impulse responses and forecast error variance decompositions (see Granger 1969; Sims 1980), heterogeneous autoregressive models with exogenous regressors (HAR-X, Corsi 2009), and a leakage-safe machine learning protocol using temporal splits, early stopping, validation-only thresholding, and SHAP-based interpretation. Using daily data from 2021 to 2025 (1462 observations across 74 assets), we document statistically significant Granger-causal relationships across layers and moderate out-of-sample predictive accuracy. We report the most informative figures, including the pipeline overview, Layer A heatmap, Layer C robustness analysis, vector autoregression variance decompositions, and the test-set precision-recall curve. Full data and figure outputs are provided in the artifact repository.

cs.LG↗