Nazreen Shah Ambalath (S A Nazreen) PhD Student, ECE IIIT Delhi Intellicom Lab, RnD Block Email: nazreens@iiitd.ac.in [CV] [Google Scholar] [LinkedIn] [GitHub] [Weights & Biases]

About Me

I am a PhD student at IIIT Delhi (since January, 2022), advised by Dr. Ranjitha Prasad. My research focuses on Federated Learning, particularly:

• Personalized Federated Learning
• Continual Federated Learning
• Unsupervised & Decentralized Federated Learning

I am a recipient of the Prime Minister’s Fellowship for Doctoral Research (SERB–FICCI). Currently, I am a Visiting Scholar (February, 2026 - July, 2026) at Wayne State University, Detroit, working with Dr. Prashant Khanduri.

Previously, I worked at ISI Kolkata (DRDO project on Hardware Trojan Detection using X-ray imaging) and at IDRBT Hyderabad on reversible data hiding in images. I completed my 5-year Integrated M.Tech in Computer Science from the University of Hyderabad.

Research Interests

• Federated Learning & Federated Optimization
• Personalization in FL
• Continual Learning & Unlearning
• Unsupervised Representation Learning
• Over-the-Air Federated Learning

Publications

• Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks
  Fathima Z., Zubair Shaban, Jamala Y., Nazreen Shah, Bharath B. N., Ranjitha Prasad
  IEEE ICASSP 2026

• Personalized Federated Autoencoders: Unsupervised Representation Learning at the Edge
  Nazreen Shah, K. Arora, A. Sethi, Ranjitha Prasad, M. Uliyar, A. G. Krishna
  ICVGIP 2025

• On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients
  Satish Kumar Keshri, Nazreen Shah, Ranjitha Prasad
  AISTATS 2025

• Robust Over-The-Air Federated Learning in Heterogeneous Networks
  Zubair Shaban, Nazreen Shah, Ranjitha Prasad
  IEEE ICASSP 2025

• Federated Probabilistic Representation Learning using Information Geometric Approach
  Nazreen Shah, Ranjitha Prasad
  CODS-COMAD 2024

• Continual Federated Learning with Aggregated Gradients
  Satish Kumar Keshri, Nazreen Shah, Ranjitha Prasad
  CODS-COMAD 2024

• Importance Sampling Based Federated Unsupervised Representation Learning
  Nazreen Shah, Prachi Goyal, Ranjitha Prasad
  IEEE ICASSP 2024

• Over-the-Air Clustered Wireless Federated Learning
  Ayush Madhan-Sohini, Divin Dominic, Nazreen Shah, Ranjitha Prasad
  IEEE Globecom Workshops 2023

Preprints

• Over-The-Air Clustered Wireless Federated Learning
  Ayush Madhan-Sohini, Divin Dominic, Nazreen Shah, Ranjitha Prasad

Academic Service

• Reviewer: ICASSP, ICC, WiML-NeurIPS, AAAI-FLCA Workshop
• Volunteer: NCC 2025 (IIT Delhi)
• IEEE SPS & IEEE WIE Member

Awards & Fellowships

• Prime Minister’s Fellowship for Doctoral Research (SERB–FICCI)
• Best Poster Award – ICDCN 2025
• Multiple travel grants (ICASSP, NeurIPS WiML, EEML, CODS-COMAD)
• Dean’s List – Best Teaching Assistant, IIIT Delhi

Teaching

• Teaching Assistant – Convex Optimization (IIIT Delhi)
• Teaching Assistant – Distributed & Federated ML (IIIT Delhi)
• Teaching Assistant – Probability & Random Processes (IIIT Delhi)

Contact

Email: nazreens@iiitd.ac.in
GitHub: github.com/nazreenshah
Website: nazreenshah.github.io