👋 Hi! I am Subhodip Panda
👨💼 I am a Senior Research Scientist at Fujitsu Research where I am a member of Security Sciences Lab (SSL). Priviously, I worked as Ph.D sciences intern at Microsoft India broadly working in the area of LLM personalization. I also worked as Ph.D research intern at Adobe Research, Bangalore working on data attribution for vision language models. Prior to this, I had the opportunity to spend a brief but enriching period as a Research Associate at Oneirix Labs, where I was involved in developing algorithms using applied mathematics and computational statistics, with a particular emphasis on their applications in Medical AI and 3D reconstruction. During my undergrad, I also worked as a research intern at Laboratory for Electro-Optics Systems (LEOS) of Indian Space Research Organization.
👨🎓 I will be completing my Ph.D from the ECE department, Indian Institute of Science (IISc), Bangalore, where I was a part of Representation Learning Lab, advised by Prof. Prathosh A.P. I am very fortunate to be mentored by some brilliant researchers (Dr. Ananda Theertha Suresh, Prof. Sai Praneeth, Prof. Shubhada Agrawal, Prof. Debabrota Basu) during current years of my Ph.D research. Before commencing my doctoral studies, I have completed my post-graduate studies in Statistics from Indian Statistical Institute (ISI), Chennai under the supervision of Prof. Sudheesh Kumar K. and undergraduate studies in ECE from Indian Institute of Engineering Science and Technology (IIEST),Shibpur.
🔍 Research Interests
🧠 My broader research interest lies in Trustworthy Machine Learning. In particular, my current thesis focuses on the design and analysis of privacy- and uncertainty-aware learning algorithms. I am curious about understanding the contribution of individual data points in the learning process and developing techniques to estimate and unlearn the effect of specific data. I believe Differential Privacy offers a powerful theoretical lens into this question, and Influence Estimation (Data Attribution), Machine Unlearning provide practical tools to achieve it.
💡 I also work on topics related to Diffusion Models and Fragility issues in Bandit Algorithms. Additionally, I am very interested in Statistical Optimal Transport, and Conformal Prediction for statistical/deep learning problems.
📚 Topics of Interest
- 🔐 Privacy: Machine Unlearning, Differential Privacy
- 🎲 Uncertainty: Conformal Prediction, Calibration
- 📘 Others: Statistics, Learning Theory, Information Theory
📫 Feel free to reach out to me via email if your interests align or you’d like to collaborate!