Machine Learning Optimization Laboratory

The Machine Learning Optimization (MILO) Lab at UTSA conducts cutting-edge research in machine learning optimization, developing robust, computationally efficient, explainable, and trustworthy solutions to tackle real-world challenges.

Our work emphasizes intelligent and practical solutions, particularly in resource-limited and challenging data environments. We develop both theory and algorithms and directly address applications in areas including remote sensing, computer vision, wireless communications, and healthcare.

Selected Current Research Topics:

• Robust Learning – Handling noisy, incomplete, and adversarial data

• Continual Learning – Adapting to new tasks and evolving data distributions

• Federated Learning – Optimizing efficiency under privacy and connectivity constraints

• Few-Shot Learning – Learning effectively from minimal, coherent data

• Multimodal Learning – Integrating diverse data sources for richer insights

• Quantum Machine Learning – Advancing quantum-enhanced optimization and learning

We aim to push the boundaries of machine learning with theoretical rigor and real-world impact.