Selected work

Representative Papers

Model Uncertainty under Non-Gaussian Errors: Bayesian Model Averaging and Selection in Stochastic Frontier Models

Jul 15, 2026

This study addresses covariate selection and model uncertainty in stochastic frontier models under non-Gaussian errors by proposing an efficient inference framework based on Bayesian model averaging and selection. Leveraging parallelized exhaustive search, Monte Carlo simulation, and a normal-exponential stochastic frontier specification, the paper systematically evaluates the impact of asymmetric disturbances on posterior inference. The findings demonstrate that, in moderate-dimensional covariate settings, a well-designed exhaustive search strategy outperforms random search. Moreover, explicitly modeling the stochastic frontier structure significantly enhances the robustness and accuracy of model-averaged estimates across varying efficiency-to-noise ratios and signal strengths.

0 citationsRead paper

EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning

Jul 07, 2026

This work addresses the challenge that existing graph embedding methods struggle to accurately recover the geodesic geometry of manifolds under non-uniform sampling or in the presence of spurious short-circuit edges. The authors propose a path ensemble based on maximum-entropy random walks, constructing a free-energy distance by aggregating over all k-step paths. In the short-time limit, this distance approximates the squared geodesic distance, effectively balancing local neighborhood structure with global geometry. By integrating Varadhan’s heat kernel formula with symmetric kernel Gram decomposition, the method establishes a precise connection between free-energy distances and kernel methods. Scalability is enhanced through landmark-based projection and diffusion-potential pseudo-time. Experiments demonstrate that the approach significantly outperforms current diffusion- or shortest-path-based techniques on both synthetic manifolds and single-cell datasets, exhibiting superior robustness in preserving geodesic structure under non-uniform sampling and branching trajectory scenarios.

0 citationsRead paper

Diversity in Schumpeterian games

Dec 19, 2025

This study investigates how diversity changes induced by new product introductions drive the evolution of economic systems, focusing on the dynamic reconfiguration of an evolutionary stable state—termed the “Schumpeterian state”—in which innovators and imitators coexist under Schumpeterian competition. Method: Employing evolutionary game theory and population-dynamic modeling, the paper formally treats diversity change as a core structural driver of innovation, moving beyond conventional reliance on technological differentiation or cost advantages alone. Contribution/Results: Evolutionary stability analysis demonstrates that the level of product diversity fundamentally reshapes equilibrium composition: high diversity reinforces innovator dominance and delays creative destruction, whereas low diversity accelerates imitative diffusion and technological turnover. By endogenizing diversity as a strategic parameter, the framework establishes a novel theoretical benchmark for analyzing industry evolution paths, technology life cycles, and the efficacy of innovation policy interventions.

0 citationsRead paper

Boltzmann Price: Toward Understanding the Fair Price in High-Frequency Markets

Jul 13, 2025

This paper addresses the problem of defining fair price and modeling price dynamics in high-frequency markets. Methodologically, it proposes a parametric price model grounded in the principle of maximum entropy, directly deriving fair price from order-book top-side bid-ask volume imbalance, and constructing a dynamic model wherein drift and volatility are driven by volume–price disequilibrium—thereby unifying the evolution of price, bid–ask spread, and trading volume. Its key contributions are threefold: (i) it is the first to apply the maximum entropy principle to define fair price in high-frequency markets, endogenizing the drift term via order-book imbalance; (ii) it naturally generates heavy-tailed return distributions and high-order kurtosis, overcoming the limitations of conventional constant-volatility models; and (iii) numerical simulations and empirical calibration to historical equity data confirm its ability to accurately replicate stylized market features, significantly enhancing explanatory power for high volatility and extreme events.

0 citationsRead paper

Recent publications

Latest Papers

Model Uncertainty under Non-Gaussian Errors: Bayesian Model Averaging and Selection in Stochastic Frontier Models

Jul 15, 2026

This study addresses covariate selection and model uncertainty in stochastic frontier models under non-Gaussian errors by proposing an efficient inference framework based on Bayesian model averaging and selection. Leveraging parallelized exhaustive search, Monte Carlo simulation, and a normal-exponential stochastic frontier specification, the paper systematically evaluates the impact of asymmetric disturbances on posterior inference. The findings demonstrate that, in moderate-dimensional covariate settings, a well-designed exhaustive search strategy outperforms random search. Moreover, explicitly modeling the stochastic frontier structure significantly enhances the robustness and accuracy of model-averaged estimates across varying efficiency-to-noise ratios and signal strengths.

0 citationsRead paper

EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning

Jul 07, 2026

This work addresses the challenge that existing graph embedding methods struggle to accurately recover the geodesic geometry of manifolds under non-uniform sampling or in the presence of spurious short-circuit edges. The authors propose a path ensemble based on maximum-entropy random walks, constructing a free-energy distance by aggregating over all k-step paths. In the short-time limit, this distance approximates the squared geodesic distance, effectively balancing local neighborhood structure with global geometry. By integrating Varadhan’s heat kernel formula with symmetric kernel Gram decomposition, the method establishes a precise connection between free-energy distances and kernel methods. Scalability is enhanced through landmark-based projection and diffusion-potential pseudo-time. Experiments demonstrate that the approach significantly outperforms current diffusion- or shortest-path-based techniques on both synthetic manifolds and single-cell datasets, exhibiting superior robustness in preserving geodesic structure under non-uniform sampling and branching trajectory scenarios.

0 citationsRead paper

Diversity in Schumpeterian games

Dec 19, 2025

This study investigates how diversity changes induced by new product introductions drive the evolution of economic systems, focusing on the dynamic reconfiguration of an evolutionary stable state—termed the “Schumpeterian state”—in which innovators and imitators coexist under Schumpeterian competition. Method: Employing evolutionary game theory and population-dynamic modeling, the paper formally treats diversity change as a core structural driver of innovation, moving beyond conventional reliance on technological differentiation or cost advantages alone. Contribution/Results: Evolutionary stability analysis demonstrates that the level of product diversity fundamentally reshapes equilibrium composition: high diversity reinforces innovator dominance and delays creative destruction, whereas low diversity accelerates imitative diffusion and technological turnover. By endogenizing diversity as a strategic parameter, the framework establishes a novel theoretical benchmark for analyzing industry evolution paths, technology life cycles, and the efficacy of innovation policy interventions.

0 citationsRead paper

Boltzmann Price: Toward Understanding the Fair Price in High-Frequency Markets

Jul 13, 2025

This paper addresses the problem of defining fair price and modeling price dynamics in high-frequency markets. Methodologically, it proposes a parametric price model grounded in the principle of maximum entropy, directly deriving fair price from order-book top-side bid-ask volume imbalance, and constructing a dynamic model wherein drift and volatility are driven by volume–price disequilibrium—thereby unifying the evolution of price, bid–ask spread, and trading volume. Its key contributions are threefold: (i) it is the first to apply the maximum entropy principle to define fair price in high-frequency markets, endogenizing the drift term via order-book imbalance; (ii) it naturally generates heavy-tailed return distributions and high-order kurtosis, overcoming the limitations of conventional constant-volatility models; and (iii) numerical simulations and empirical calibration to historical equity data confirm its ability to accurately replicate stylized market features, significantly enhancing explanatory power for high volatility and extreme events.

0 citationsRead paper