Curriculum Vitae
The detailed PDF verison of my CV can be found here - Curriculum Vitae
Research Interests
I seek to solve problems involving (a) proposing new algorithms involving large scale optimization and (b) mathematical analysis of deep learning algorithms using Probability Theory and High Dimensional Statistics.
Publications
- Trainable Transformer in Transformer - International Conference on Machine Learning (ICML), 2024 [paper]
- Do Transformers Parse while Predicting the Masked Word? - Empirical Methods in Natural Language Processing (EMNLP), 2023 [paper]
- Task-Specific Skill Localization in Fine-tuned Language Models - International Conference on Machine Learning (ICML), 2023 [paper]
- On the SDEs and Scaling Rules for Adaptive Gradient Algorithms - Neural Information Processing Systems (NeurIPS), 2022 [paper]
- Understanding Gradient Descent on Edge of Stability in Deep Learning - International Conference on Machine Learning (ICML), 2022 [paper]
- Learning and Generalization in RNNs - Neural Information Processing Systems (NeurIPS), 2021 [paper] [bib]
- Effect of Activation Functions on the Training of Overparametrized Neural Nets - International Conference on Learning Representations (ICLR), 2020 [paper]
- Word2Sense: Sparse Interpretable Word Embeddings - Association for Computational Linguistics (ACL), 2019 [paper] [bib]
Education
- B.Tech. in Computer Science and Engineering, 2014 - 18, Indian Institute of Technology Kharagpur
CGPA - 9.90/10 (Major GPA - 10/10), Institute Rank: 1 (out of 1400 students).
Work experience
- July 2018 - July 2020 (Expected): Research Fellow
- Microsoft Research Lab - India
- Mentors: Dr. Harsha Vardhan Simhadri and Dr. Navin Goyal
- Project group: Algorithms and Data Sciences
- Summer 2016: Summer Research Intern