Simran Kaur

According to our database, Simran Kaur authored at least 7 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Can Models Learn Skill Composition from Examples?

Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora

CoRR, 2024

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning.

Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora

CoRR, 2024

SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models.

Dingli Yu, Simran Kaur, Arushi Gupta, Jonah Brown-Cohen, Anirudh Goyal, Sanjeev Arora

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Disentangling the Mechanisms Behind Implicit Regularization in SGD.

Zachary Novack, Simran Kaur, Tanya Marwah, Saurabh Garg, Zachary Chase Lipton

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

On the Maximum Hessian Eigenvalue and Generalization.

Simran Kaur, Jeremy Cohen, Zachary Chase Lipton

Proceedings of the Proceedings on "I Can't Believe It's Not Better!, 2022

2021

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability.

Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar

Proceedings of the 9th International Conference on Learning Representations, 2021

2019

Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

Simran Kaur, Jeremy Cohen, Zachary C. Lipton

CoRR, 2019