About

Professor Alfredo Garcia is a faculty member in the Department of Industrial & Systems Engineering at Texas A&M University. He holds the Mike and Sugar Barnes Professorship III in Industrial & Systems Engineering. His research interests include game theory and dynamic optimization, with applications in electricity and communication networks. Dr. Garcia has contributed to the understanding of driver responses to automation failures, distributed networked learning with correlated data, incentive mechanisms for electricity markets, and distributed non-convex optimization, among other topics. His work focuses on developing advanced mathematical and computational methods to address complex problems in engineering systems and networks.

Research topics

• Computer Science
• Artificial Intelligence
• Reliability engineering
• Pure mathematics
• Geometry
• Mathematical analysis
• Medicine
• Combinatorics
• Biology
• Physics
• Mathematics
• Mathematical optimization
• Applied mathematics
• Engineering

Selected publications

• Distributed continuous-time unit commitment with energy storage in multi-area networks

  Electric Power Systems Research · 2025-02-18 · 2 citations

  articleSenior author
  PublisherDOI

• A trust-region approach for computing Pareto fronts in multiobjective derivative-free optimization

  Optimization Letters · 2024-11-29 · 5 citations

  articleOpen accessSenior author

  Abstract This paper presents a modified trust-region approach for computing approximations to the complete Pareto front of multiobjective derivative-free optimization problems. It is assumed that the derivatives of the objective function components are not available, impossible or very expensive to estimate, such as in simulation optimization, bandit optimization, and adversarial black-box machine learning. The algorithm alternates between two main steps, namely, the extreme point step and the scalarization step, until predefined stopping criteria are met. The goal of the extreme point step is to expand the approximation to the complete Pareto front, by moving towards the extreme points of it, corresponding to the individual minimization of each objective function component. The scalarization step attempts to minimize the size of gaps in the Pareto front approximation, by solving a suitable scalarization problem. The scalarization step includes a pivotal additional step, referred to as the middle point step. This step plays a significant role in determining initial points for solving the scalarization problem. To overcome the absence of derivatives, a new technique based on polynomial interpolation and minimum Frobenius norm approaches is proposed to build models that approximate different objective function components. The convergence analysis is well established, even with the extra complexity introduced by the challenge of lacking derivative information. Numerical results are presented, indicating that this algorithm is efficiently and robustly competitive against state-of-the-art multiobjective derivative-free optimization algorithms that also aim to approximate complete Pareto fronts.

  PublisherOA PDFDOI

• Resolving uncertainty on the fly: modeling adaptive driving behavior as active inference

  Frontiers in Neurorobotics · 2024-03-21 · 18 citations

  articleOpen access

  Understanding adaptive human driving behavior, in particular how drivers manage uncertainty, is of key importance for developing simulated human driver models that can be used in the evaluation and development of autonomous vehicles. However, existing traffic psychology models of adaptive driving behavior either lack computational rigor or only address specific scenarios and/or behavioral phenomena. While models developed in the fields of machine learning and robotics can effectively learn adaptive driving behavior from data, due to their black box nature, they offer little or no explanation of the mechanisms underlying the adaptive behavior. Thus, generalizable, interpretable, computational models of adaptive human driving behavior are still rare. This paper proposes such a model based on active inference, a behavioral modeling framework originating in computational neuroscience. The model offers a principled solution to how humans trade progress against caution through policy selection based on the single mandate to minimize expected free energy. This casts goal-seeking and information-seeking (uncertainty-resolving) behavior under a single objective function, allowing the model to seamlessly resolve uncertainty as a means to obtain its goals. We apply the model in two apparently disparate driving scenarios that require managing uncertainty, (1) driving past an occluding object and (2) visual time-sharing between driving and a secondary task, and show how human-like adaptive driving behavior emerges from the single principle of expected free energy minimization.

  PublisherOA PDFDOI

• Federated Multi-task Learning in Distributed Networks

  2024-12-15

  articleSenior author

  We consider a Distributed Federated multitask learning scheme that accounts for multiple linear model estimation tasks with heterogeneous and/or correlated data streams. We assume that nodes can be partitioned into groups corresponding to different learning tasks and communicate according to a directed network topology. Each node estimates a linear model asynchronously and is subject to local (within-group) regularization and global (across groups) regularization terms targeting noise reduction and generalization performance improvement, respectively. We provide a finite-time characterization of the convergence of the estimators and task relation and illustrate the scheme’s general applicability of random field temperature estimation.

  PublisherDOI

• FedGlu: A personalized federated learning-based glucose forecasting algorithm for improved performance in glycemic excursion regions

  arXiv (Cornell University) · 2024-08-25 · 1 citations

  preprintOpen access

  Continuous glucose monitoring (CGM) devices provide real-time glucose monitoring and timely alerts for glycemic excursions, improving glycemic control among patients with diabetes. However, identifying rare events like hypoglycemia and hyperglycemia remain challenging due to their infrequency. Moreover, limited access to sensitive patient data hampers the development of robust machine learning models. Our objective is to accurately predict glycemic excursions while addressing data privacy concerns. To tackle excursion prediction, we propose a novel Hypo-Hyper (HH) loss function, which significantly improves performance in the glycemic excursion regions. The HH loss function demonstrates a 46% improvement over mean-squared error (MSE) loss across 125 patients. To address privacy concerns, we propose FedGlu, a machine learning model trained in a federated learning (FL) framework. FL allows collaborative learning without sharing sensitive data by training models locally and sharing only model parameters across other patients. FedGlu achieves a 35% superior glycemic excursion detection rate compared to local models. This improvement translates to enhanced performance in predicting both, hypoglycemia and hyperglycemia, for 105 out of 125 patients. These results underscore the effectiveness of the proposed HH loss function in augmenting the predictive capabilities of glucose predictions. Moreover, implementing models within a federated learning framework not only ensures better predictive capabilities but also safeguards sensitive data concurrently.

  PublisherOA PDFDOI

• Multi-agent reinforcement learning for multi-area power exchange

  Electric Power Systems Research · 2024-07-09 · 1 citations

  article
  PublisherDOI

• Retraction-Free Decentralized Non-convex Optimization with Orthogonal Constraints

  arXiv (Cornell University) · 2024-05-19

  preprintOpen access

  In this paper, we investigate decentralized non-convex optimization with orthogonal constraints. Conventional algorithms for this setting require either manifold retractions or other types of projection to ensure feasibility, both of which involve costly linear algebra operations (e.g., SVD or matrix inversion). On the other hand, infeasible methods are able to provide similar performance with higher computational efficiency. Inspired by this, we propose the first decentralized version of the retraction-free landing algorithm, called \textbf{D}ecentralized \textbf{R}etraction-\textbf{F}ree \textbf{G}radient \textbf{T}racking (DRFGT). We theoretically prove that DRFGT enjoys the ergodic convergence rate of $\mathcal{O}(1/K)$, matching the convergence rate of centralized, retraction-based methods. We further establish that under a local Riemannian PŁ condition, DRFGT achieves a much faster linear convergence rate. Numerical experiments demonstrate that DRFGT performs on par with the state-of-the-art retraction-based methods with substantially reduced computational overhead.

  PublisherOA PDFDOI

• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment

  arXiv (Cornell University) · 2024-06-11

  preprintOpen access

  Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into successive stages, such as supervised fine-tuning (SFT), reward modeling (RM), and reinforcement learning (RL), each performing one specific learning task. Such a sequential approach results in serious issues such as significant under-utilization of data and distribution mismatch between the learned reward model and generated policy, which eventually lead to poor alignment performance. We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF), capable of integrating both human preference and demonstration to train reward models and the policy. The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms such as RLHF and Directly Policy Optimization (DPO), and only requires minor changes to the existing alignment pipelines. We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo. We observe that the proposed solutions outperform the existing alignment algorithms such as RLHF and DPO by large margins, especially when the amount of high-quality preference data is relatively limited.

  PublisherOA PDFDOI

• Regularized Q-Learning with Linear Function Approximation

  arXiv (Cornell University) · 2024-01-26

  preprintOpen access

  Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation, the convergence properties of learning algorithms for regularized MDPs (e.g. soft Q-learning) are not well understood because the composition of the regularized Bellman operator and a projection onto the span of basis vectors is not a contraction with respect to any norm. In this paper, we consider a bi-level optimization formulation of regularized Q-learning with linear functional approximation. The {\em lower} level optimization problem aims to identify a value function approximation that satisfies Bellman's recursive optimality condition and the {\em upper} level aims to find the projection onto the span of basis vectors. This formulation motivates a single-loop algorithm with finite time convergence guarantees. The algorithm operates on two time-scales: updates to the projection of state-action values are `slow' in that they are implemented with a step size that is smaller than the one used for `faster' updates of approximate solutions to Bellman's recursive optimality equation. We show that, under certain assumptions, the proposed algorithm converges to a stationary point in the presence of Markovian noise. In addition, we provide a performance guarantee for the policies derived from the proposed algorithm.

  PublisherOA PDFDOI

• Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees

  Operations Research · 2024-09-19 · 2 citations

  articleSenior author

  Researchers have introduced a new algorithm to estimate structural models of dynamic decisions by human agents, addressing the challenge of high computational complexity. Traditionally, this task involves a nested structure: an inner problem identifying an optimal policy and an outer problem maximizing a measure of fit. Previous methods have struggled with large discrete state spaces or high-dimensional continuous state spaces, often sacrificing reward estimation accuracy. The new approach combines policy improvement with a stochastic gradient step for likelihood maximization, ensuring accurate reward estimation without compromising computational efficiency. This single-loop algorithm, designed to handle high-dimensional state spaces, converges to a stationary solution with finite-time guarantees. When the reward is linearly parameterized, it approximates the maximum likelihood estimator sublinearly, offering a robust solution for complex decision modeling tasks.

  PublisherDOI

Recent grants

• Collaborative Research: Unlocking Capacity for Wireless Networks Using Cooperative and Cognitive Techniques

  NSF · $40k · 2010–2012

• Smart Markets for Black-box Capacity Allocation

  NSF · $218k · 2018–2020

• CIF: Small: Dynamic Pricing of Interference in Cognitive Radio Networks

  NSF · $436k · 2010–2014

• CT-ISG: The Economics of Internet Security: Theoretical and Empirical Analysis

  NSF · $385k · 2007–2010

• I/UCRC: Collaborative Research: Unlocking Spectrum Efficiency for Future Wireless Networks

  NSF · $40k · 2012–2013

Frequent coauthors

• Mingyi Hong

  28 shared

• Natalia Fabra

  9 shared

• Jorge Barrera

  University of Virginia

  9 shared

• Shi Pu

  8 shared

• Ceyhun Eksin

  8 shared

• Anthony D. McDonald

  University of Wisconsin–Madison

  7 shared

• Robert L. Smith

  University of Michigan–Ann Arbor

  7 shared

• Lingzhou Hong

  7 shared

Labs

• Wm Michael Barnes '64 Department of Industrial & Systems Engineering at Texas A&M UniversityPI

Education

• D.E.A Automatique et Informatique Industrielle, Laboratoire d'analyse et d'architecture des systèmes

  Université Paul Sabatier

  1992

• Ingeniero Eléctrico, Ingenieria Electrica

  Universidad de los Andes

  1990