Praneeth Vepakomma

Praneeth Vepakomma is an active researcher in the field of machine learning with a strong publication record spanning from 2015 to the present. His work primarily focuses on privacy-preserving distributed learning systems, with particular emphasis on federated learning, split learning, and techniques for maintaining data privacy while enabling collaborative AI development.

His research interests center around developing efficient and privacy-preserving machine learning frameworks. Vepakomma has made significant contributions to federated learning optimization, split learning architectures, and differential privacy techniques for deep learning systems. His recent work has increasingly focused on adapting these techniques for large language models, addressing communication efficiency challenges and privacy concerns in distributed fine-tuning scenarios.

Analysis of his publication trends reveals a clear trajectory from foundational work in privacy-preserving machine learning (2015-2019) to increasingly sophisticated approaches for distributed learning systems (2020-2025). His recent publications demonstrate a strong focus on solving practical challenges in federated and split learning for large language models, with particular attention to communication efficiency, privacy guarantees, and architectural innovations for heterogeneous environments.

Vepakomma has established a robust collaborative network, most notably with Ramesh Raskar (50+ co-authored papers), indicating a long-standing research partnership. His work bridges theoretical foundations with practical implementations, making significant contributions to the advancement of privacy-preserving distributed machine learning.