👋 Hi! I am Subhodip Panda
👨🎓 I am a final year Ph.D student at Representation Learning Lab of ECE department, Indian Institute of Science (IISc), Bangalore, 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.
👨💼 I have gained experience through multiple full-time and internship roles in industry as well. I was a Ph.D research intern at Adobe Research, Bangalore working on data attribution for vision language models. Before 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. 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 degree this year and currently seeking full-time research positions. Here is my CV. Feel free to reachout if you have any relevant open positions!
🔍 Research Interests
🧠 My broader research interest lies in Trustworty Machine Learning. Particulary my current thesis focus has been designing and analyzing privacy- and uncertainty-aware learning algorithms. I am particularly 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 Opitmal 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!