I've been working on...
- how to learn useful models in the presence of unreliable data
- how to employ data augmentation at test-time
- how to improve the interpretability of black-box models
Former intern at Borealis AI, D.E. Shaw Research, Counsyl and Aetion. You can find my CV here or email me at divyas at mit dot edu, or both! This interest map summarizes questions I care about.