Scholar
Adityanarayanan Radhakrishnan
Google Scholar ID: jd7_Ed0AAAAJ
MIT Mathematics, Broad Institute of MIT and Harvard
Citations & Impact
Citations
1,000
H-index
13
i10-index
20
Publications
20
Co-authors
15
list available
Contact
Publications
Resume (English only)
Research Experience
- In the field of AI, focuses on understanding feature learning (the ability of AI models to discover patterns from data), with current research concentrating on discovering general mechanisms (like the Average Gradient Outer Product – AGOP) that can help better understand the structure in data learned by large-scale AI systems. Also interested in kernel machines, unsupervised/self-supervised learning, and infinite width/depth limits of neural networks. In terms of biological applications, works on developing algorithms to discover and characterize cellular programs across various disease contexts, with a current focus on using million-to-billion scale single-cell RNA sequencing datasets to understand how these programs drive cell state and function and how they are altered in disease contexts.
Background
- Assistant Professor at MIT Math; Associate Member at the Broad Institute of MIT and Harvard. Research interests include advancing the mathematical foundations of AI, particularly in feature learning, and developing novel algorithms for biomedical applications.
