black-box optimization

Learning under Limited Information across Federated, Multi-Agent, and LLM Settings

Salma Kharrat, Ph.D. Student, Computer Science

May 7, 15:00 - 16:45

B3 R5220

Federated learning personalized learning decentralized learning Reinforcement Learning black-box optimization prompt optimization decentralized systems combinatorial optimization observability inference Trustworthy AI trustworthy machine learning intelligent systems LLM

This dissertation studies learning under structural information constraints across three major paradigms: federated learning, cooperative multi-agent reinforcement learning, and black-box optimization of large language models.

Reinforcement Learning and Optimization in Large Action Spaces under Limited Feedback

Fares Fourati, Ph.D. Student, Electrical and Computer Engineering

Apr 29, 15:00 - 16:45

B2 R5209

Reinforcement Learning machine learning combinatorial multi-armed bandits large action spaces limited feedback efficient exploration submodular optimization black-box optimization global optimization

This dissertation develops theoretical foundations and scalable algorithms for reinforcement learning and optimization in large decision spaces under limited feedback.

Salma Kharrat

Ph.D. Student, Computer Science

Federated learning Trustworthy AI trustworthy machine learning intelligent systems decentralized systems combinatorial optimization personalized learning decentralized learning Reinforcement Learning observability inference black-box optimization LLM prompt optimization

Fares Fourati

Ph.D. Student, Electrical and Computer Engineering

machine learning Deep learning Reinforcement Learning artificial intelligence combinatorial multi-armed bandits intelligent systems black-box optimization

Fares Fourati is a Ph.D. student at the King Abdullah University of Science and Technology (KAUST), under the supervision of Professor Mohamed-Slim Alouini.