Hello! I am a first-year Masters Student in the Computer Science and Engineering Department at Michigan State University pursuing my masters degree under the supervision of Dr. Vishnu Boddeti. I am extremely lucky to have amazing colleagues at Human Analysis Lab. In my past life I have received my bachelor’s degree from the Indian Institute of Technology, Guwahati Guwahati, India.
My interest lies in the field of algorithmic fairness, along with its interconnected areas such as group fairness, distribution shift analysis, machine unlearning, debiasing, spurious correlations, and causality.
Significant advancements in the field of machine learning, particularly in the development of transformative architectures such as transformers and the creation of large-scale models like CLIP and GPT-4, have undeniably pushed the boundaries of AI capabilities. However, a profound challenge remains in comprehending the underlying behavior of these models. This challenge is intrinsically linked to our quest to understand how humans transfer knowledge across diverse domains. A line of attack in this pursuit is model fairness, ensuring equitable treatment of all groups, contributes to the model’s ability to robustly navigate shifts in group distribution. Pattern Unrecognition is one such attempt to study classical Machine Learning models from the lens of distribution shift. Second line of attack is imperative that memorization leads to lower generalization. Memorization also poses a legal concern when dealing with sensitive user data, which poses an increasing concern in today’s world. To address this I am currenly working on Machine Unlearning problem.