Institution profile

CUNEF Universidad

Academic institutioneurope · es
Official website
Research library8linked papers
Opportunities0open roles
Selected work

Representative Papers

Non-monotonic causal discovery with Kolmogorov-Arnold Fuzzy Cognitive Maps

Apr 06, 2026

Traditional fuzzy cognitive maps (FCMs) struggle to model non-monotonic causal relationships due to their reliance on scalar edge weights and monotonic activation functions, rendering them incapable of capturing saturation effects or periodic dynamics. To address this limitation, this work proposes the Kolmogorov–Arnold Fuzzy Cognitive Map (KA-FCM), which for the first time integrates the Kolmogorov–Arnold representation theorem into the FCM framework. By replacing static scalar weights with learnable univariate B-spline functions, KA-FCM shifts nonlinearity into the causal influence stage, enabling direct modeling of arbitrary non-monotonic dependencies without increasing graph density or introducing hidden layers. The approach achieves high accuracy while preserving interpretability. Empirical results on Yerkes–Dodson law reasoning, symbolic regression, and chaotic time series prediction demonstrate that KA-FCM significantly outperforms conventional FCMs, matching the performance of multilayer perceptrons and allowing explicit extraction of underlying mathematical laws.

0 citationsRead paper

Step-Size Decay and Structural Stagnation in Greedy Sparse Learning

Mar 08, 2026

This work investigates the impact of step-size scheduling on residual dynamics in low-dimensional sparse regression, where excessively fast-decaying learning rates can cause greedy algorithms to suffer from structural stagnation and fail to converge. Focusing on a realizable regression setting with controllable feature coherence, the study integrates greedy approximation theory in Hilbert spaces, coherence analysis, and numerical experiments to systematically examine this phenomenon. The paper unveils, for the first time, the mechanism by which over-decaying step sizes induce structural stagnation and derives an explicit lower bound on the residual norm. Both theoretical analysis and empirical results demonstrate that feature coherence significantly modulates this effect, offering new insights for designing effective step-size schedules in greedy algorithms.

0 citationsRead paper

Quantifying displacement: a gentrification's consequence via persistent homology

Dec 11, 2025

Conventional methods struggle to quantify latent, asynchronous, and motivationally opaque population displacement in gentrification—especially over long temporal scales. Method: We propose the first topology-based modeling framework grounded exclusively on publicly available address-change records. It constructs four types of spatiotemporal cubical complexes, jointly encoding geographic and temporal dimensions, and applies persistent homology and topological feature extraction to yield computable representations of displacement. Contribution: This work overcomes longstanding reliance on surveys or longitudinal tracking by introducing topological data analysis (TDA) systematically into gentrification research for the first time. Applied to a 20-year Madrid case study, it accurately identifies displacement-prone neighborhoods and years, uncovering structural migration patterns invisible in raw data. The approach establishes a novel paradigm for quantifying urban inequality through scalable, privacy-preserving, infrastructure-derived mobility signals.

0 citationsRead paper
Recent publications

Latest Papers

Non-monotonic causal discovery with Kolmogorov-Arnold Fuzzy Cognitive Maps

Apr 06, 2026

Traditional fuzzy cognitive maps (FCMs) struggle to model non-monotonic causal relationships due to their reliance on scalar edge weights and monotonic activation functions, rendering them incapable of capturing saturation effects or periodic dynamics. To address this limitation, this work proposes the Kolmogorov–Arnold Fuzzy Cognitive Map (KA-FCM), which for the first time integrates the Kolmogorov–Arnold representation theorem into the FCM framework. By replacing static scalar weights with learnable univariate B-spline functions, KA-FCM shifts nonlinearity into the causal influence stage, enabling direct modeling of arbitrary non-monotonic dependencies without increasing graph density or introducing hidden layers. The approach achieves high accuracy while preserving interpretability. Empirical results on Yerkes–Dodson law reasoning, symbolic regression, and chaotic time series prediction demonstrate that KA-FCM significantly outperforms conventional FCMs, matching the performance of multilayer perceptrons and allowing explicit extraction of underlying mathematical laws.

0 citationsRead paper

Step-Size Decay and Structural Stagnation in Greedy Sparse Learning

Mar 08, 2026

This work investigates the impact of step-size scheduling on residual dynamics in low-dimensional sparse regression, where excessively fast-decaying learning rates can cause greedy algorithms to suffer from structural stagnation and fail to converge. Focusing on a realizable regression setting with controllable feature coherence, the study integrates greedy approximation theory in Hilbert spaces, coherence analysis, and numerical experiments to systematically examine this phenomenon. The paper unveils, for the first time, the mechanism by which over-decaying step sizes induce structural stagnation and derives an explicit lower bound on the residual norm. Both theoretical analysis and empirical results demonstrate that feature coherence significantly modulates this effect, offering new insights for designing effective step-size schedules in greedy algorithms.

0 citationsRead paper

Quantifying displacement: a gentrification's consequence via persistent homology

Dec 11, 2025

Conventional methods struggle to quantify latent, asynchronous, and motivationally opaque population displacement in gentrification—especially over long temporal scales. Method: We propose the first topology-based modeling framework grounded exclusively on publicly available address-change records. It constructs four types of spatiotemporal cubical complexes, jointly encoding geographic and temporal dimensions, and applies persistent homology and topological feature extraction to yield computable representations of displacement. Contribution: This work overcomes longstanding reliance on surveys or longitudinal tracking by introducing topological data analysis (TDA) systematically into gentrification research for the first time. Applied to a 20-year Madrid case study, it accurately identifies displacement-prone neighborhoods and years, uncovering structural migration patterns invisible in raw data. The approach establishes a novel paradigm for quantifying urban inequality through scalable, privacy-preserving, infrastructure-derived mobility signals.

0 citationsRead paper