Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


María-Luisa Pérez-Delgado has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Controllability and trainability in VQC: A DLA framework for optimal expressivity

    by Pablo Vilaboy-Sachocos, Roberto Casado, Jesús-Ángel Román-Gallego, María-Luisa Pérez-Delgado, Moisés-Alberto García-Núñez, Juan M Corchado

    Variational quantum circuits are a central framework in quantum machine learning, yet their trainability remains poorly understood, particularly in relation to circuit expressivity. In this work, we develop a unified framework that connects controllability and trainability through the structure of the dynamical Lie algebra (DLA) associated with a given circuit architecture. We show that while increasing controllability enhances expressivity, it may simultaneously degrade optimization due to concentration effects leading to vanishing gradients. Conversely, strongly constrained architectures may preserve large gradients, but their performance depends critically on the alignment between the induced algebraic structure and the learning task. We formalize this trade-off by introducing the notion of trainability-efficient controllability, which characterizes intermediate regimes where the DLA is sufficiently expressive while avoiding excessive dynamical complexity. Theoretical results establish that full controllability is not necessary for achieving optimal task performance, and that proper Lie subalgebras can be sufficient under appropriate conditions. These findings are supported by numerical experiments on representative architectures exhibiting distinct controllability regimes. Our results provide empirical evidence for a non-monotonic relationship between controllability and trainability, and highlight that optimal performance is achieved when the structure of the DLA is aligned with the requirements of the learning task.

  • Open Access

    Lie-theoretic structure of parameter gradients in variational quantum circuits

    by María-Luisa Pérez-Delgado, Roberto Casado

    Variational quantum circuits are a central paradigm of quantum machine learning and near-term quantum computing, yet their practical optimization is often limited by strongly suppressed parameter gradients. Dynamical Lie algebras provide a rigorous description of the infinitesimal directions accessible to a variational architecture, but dynamical accessibility alone does not determine the gradient signal exposed by an actual circuit parametrization. In this work, we develop a Lie-theoretic description of parameter-gradient structure that separates four successive mechanisms: dynamical accessibility, observable visibility, state-dependent activation, and local parameter realization. The optimization observable determines which accessible directions can influence the objective and how strongly they couple to it, while the quantum state selects which of these response modes are locally activated. This information is then pulled back through the circuit parametrization to recover the actual parameter gradients. The resulting construction yields an exact modal decomposition of the accessible gradient signal, a hierarchy of structural bounds, and a natural description of state averaging. An analytical single-qubit example and controlled numerical experiments validate the successive levels of the hierarchy and show that accessible Lie dimension alone is insufficient to characterize the parameter-gradient scale. The results support a mechanism-based view of variational trainability in which parameter gradients emerge from the interaction between accessible dynamics, observable coupling, quantum-state activation, and circuit parametrization.

  • Open Access

    Federated transformer autoencoder with reinforcement learning–tuned thresholding in IoT and network

    by Fouad Ailabouni, Jesús-Ángel Román-Gallego, María-Luisa Pérez-Delgado

  • Open Access

    An Exploratory Analysis of Managerial Competencies Through 360° Evaluation and Linear Regression: A Case Study and Preliminary Validation of the MLPD Model

    by Esteban Maurin Saldaña, María-Luisa Pérez-Delgado, Javiera Canales

    The assessment of managerial competencies in information technology (IT) organizations requires robust and validated instruments capable of predicting performance in volatile, uncertain, complex, and ambiguous environments. This study presents a preliminary validation of the MLPD (Machine Learning Predictive Development) model, which integrates 360° multidimensional evaluation, situational awareness, and exploratory analytics. Conceived as a pilot application and proof-of-concept, the research was conducted within the IT organization of a Chilean Defense Institution responsible for the management and administration of information and communication technologies. This study aims to determine how the three most commonly cited managerial competency domains (Transformational Leadership, Situational Awareness, and Collaborative Management) are weighted in additive models of 360° performance evaluation in a defense IT context, and also seeks to determine whether these weightings differ between civilian and military evaluators. Although the study focuses on a specialized case study with a limited sample of 9 IT leaders, the robustness of the preliminary findings is supported by the analysis of 165 rating records from 360° evaluations clustered within 9 leaders. Through this granular data set, multiple linear regression models were developed to examine the predictive relationships among three core competency domains—Transformational Leadership, Situational Awareness, and Collaborative Management—and their impact on overall managerial performance. The results identify Collaborative Management as the strongest predictor of performance, and highlight significant differences between civilian and military evaluators. This finding challenges conventional assumptions about leadership effectiveness in IT contexts and suggests that horizontal coordination capabilities are more critical than vertical authority. These preliminary results validate the model’s internal structure within a highly hierarchical environment, establishing a foundational benchmark for future large-scale applications of the MLPD model in diverse organizational contexts.


  • The Intersection of Insider Threats and Zero-Day Attacks: An Analytical Review

    by Fouad Ailabouni, Jesús-Ángel Román-Gallego, María-Luisa Pérez-Delgado

  • A Review of the State of the Art on Zero-Day Attacks in IoT Devices

    by Fouad Ailabouni, Jesús-Ángel Román-Gallego, María-Luisa Pérez-Delgado

  • Open Access

    Boundary-Aware Contrastive Learning for Log Anomaly Detection

    by Fouad Ailabouni, Jesús-Ángel Román-Gallego, María-Luisa Pérez-Delgado, Laura Grande Pérez

    Log anomaly detection in modern distributed systems is challenging. Anomalous behaviors are rare. Manual labeling is expensive. Session boundaries are often set by fixed heuristics before model training. This fixed-boundary assumption is problematic because segmentation errors propagate into representation learning and cannot be corrected during optimization. To address this, this paper proposes BASN (Boundary-Aware Sessionization Network), a boundary-aware contrastive learning framework that jointly learns session boundaries and anomaly representations using a differentiable soft-reset mechanism. BASN does not treat sessionization as a separate step. Instead, it predicts boundary probabilities from event semantics and temporal gaps, then modulates end-to-end session-state updates. The session representations are optimized with self-supervised contrastive learning, enabling effective zero-shot anomaly detection and few-shot adaptation. Experiments on four benchmark datasets (BGL, HDFS, OpenStack, SSH) show strong zero-shot performance (area under the receiver operating characteristic curve, AUROC 0.935–0.975) and boundary alignment with expert-validated proxy segmentation (boundary F1 0.825–0.877). Comparative gains over baselines are reported in the article after bibliography correction, baseline verification, and expanded statistical analysis. BASN is also computationally efficient, requiring less than 10 ms per session on a Graphics Processing Unit (GPU) and less than 45 ms on a Central Processing Unit (CPU). This is compatible with real-time inference needs in the evaluated settings. However, cross-system transfer AUROC (0.735–0.812) remains below in-domain performance. Domain-specific adaptation is still needed for deployment in environments that differ greatly from the training domain.

  • Open Access

    Automatic Identification of Culturally Relevant Buildings Using Artificial Intelligence for Smart Tourism Applications

    by Jesús-Ángel Román-Gallego, Jaime Sainz-Argente, María-Luisa Pérez-Delgado, Miguel-Ángel Conde, Roberto Casado-Vara

  • Open Access

    Grey wolf optimization for color quantization

    by María-Luisa Pérez-Delgado, Jesús-Ángel Román-Gallego, M. Emre Celebi

  • Median cut color quantization algorithm: retrospective

    by M. Emre Celebi, María-Luisa Pérez-Delgado

    Color quantization, reducing the number of distinct colors in a given image with minimal distortion, is a common image processing operation with many applications in visual computing. Heckbert’s median cut algorithm, which dates back to the early 1980s, is generally considered the first true color quantization algorithm. Heckbert’s seminal work generated numerous subsequent studies extending his algorithm in various ways. In this retrospective, we present a detailed analysis of the median cut algorithm and demonstrate how it influenced later color quantization, vector quantization, and data clustering algorithms.