Hi, I’m Simran!
I am a PhD Candidate in the CS department at Princeton University, where I am fortunate to be advised by Professor Sanjeev Arora. I am also a member of Princeton Language and Intelligence. I am broadly interested in the theoretical and empirical foundations of machine learning.
Previously, I completed my BS in Artificial Intelligence at Carnegie Mellon University’s School of Computer Science, where I was advised by Professor Zachary Lipton in the ACMI Lab.
In my spare time, I enjoy running, painting, and baking biscotti!
Papers
(2024).
Can Models Learn Skill Composition from Examples?.
NeurIPS 2024.
(2024).
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning.
[Oral] Compositional Learning Workshop at NeurIPS 2024.
(2023).
Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models.
ICLR 2024. NeurIPS DistShift Workshop 2023.
(2022).
Disentangling the Mechanisms Behind Implicit Regularization in SGD.
ICLR 2023. [Spotlight] NeurIPS HOOML Workshop 2022.
(2022).
On the Maximum Hessian Eigenvalue and Generalization.
[Contributed Talk] NeurIPS ICBINB Workshop 2022.
(2021).
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability.
ICLR 2021. NeurIPS OPT Workshop 2020.
(2019).
Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?.
NeurIPS SEDL Workshop 2019.
Teaching
Teaching Assistant for COS 324 Introduction to Machine Learning
Princeton University
JRW (Junior Research Workshop) TA for Fall 2023.
Teaching Assistant for 15281 Artificial Intelligence Representation & Problem Solving
Carnegie Mellon University
Head TA for Spring 2021, Fall 2021, and Spring 2022.
Teaching Assistant for 10301/10601 Introduction to Machine Learning (Undergraduate and Graduate Level)
Carnegie Mellon University