Publications

Holistic Artificial Intelligence in Medicine; improved performance and explainability

With the increasing interest in deploying Artificial Intelligence in medicine, our group previously introduced HAIM (Holistic AI in …

Periklis Petridis, Georgios Margaritis, Vasilis Stoumpou, Dimitris Bertsimas

Efficient Domain Adaptation of Multimodal Embeddings Using Contrastive Learning

Recent advancements in machine learning (ML), natural language processing (NLP), and foundational models have shown promise for …

Georgios Margaritis, Periklis Petridis, Dimitris J. Bertsimas

Global Optimization: A Machine Learning Approach

Many approaches for addressing global optimization problems typically rely on relaxations of nonlinear constraints over specific …

Dimitris Bertsimas, Georgios Margaritis

Robust and Adaptive Optimization Under a Large Language Model Lens

A novel approach combining robust optimization with large language models to enhance decision-making under uncertainty with improved interpretability.

Dimitris Bertsimas, Georgios Margaritis

Differentially Private Data Synthesis Using Variational Autoencoders

This thesis presents a novel approach to differentially private data synthesis using variational autoencoders (VAEs). We develop a …

Georgios Margaritis