Research Interests
Inspired from how humans learn, I am interested in developing practical algorithms and architectures that enable machine learning (ML) systems to correct themselves and learn on the fly from expert feedback. I am also interested in how we can ensure models learn robust rules for applications with a large user base.
|
Publications
* denotes equal contribution, + denotes signifcant contribution
|
Leveraging Domain-Specific Rules In Deep Learning Models
Ananth Balashankar,
Ankit Bhawdwaj,
Neelabh Madan+,
Thomas Wies,
Lakshmi Subramanian ,
Under Review: AISTATS 2025
|
|
Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction
Anirudh Buvanesh*,
Rahul Chand*,
Jatin Prakash*,
Bhawna Paliwal,
Mudit Dhawan,
Neelabh Madan,
Deepesh Hada,
Yashoteja Prabhu,
Manik Varma,
ICLR 2024
Paper /
Code
|
|
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration
Neelabh Madan*,
Ramya Hebbalaguppe*,
Jatin Prakash*,
Chetan Arora
CVPR 2022 Oral (4.2% acceptance rate)
Paper /
Code
|
|