About Me

I'm a fifth year PhD candidate in the Department of Computer Science at Princeton University. I'm fortunate to be advised by Sanjeev Arora. My research focuses on machine learning, and deep learning in particular. More specifically, I am interested in explainable AI ( saliency maps, influence functions, data models), generalization, and generative models with a recent interest in appliying saliency to large language models. I received my BSc from Columbia University in 2016 in Operations Research : Financial Engineering and Computer Science, with minors in Applied Math and Economics. I received my MSc at Columbia in 2018 in Machine Learning.

Publications and Manuscripts

* denotes equal contribution

• Udaya Ghai*, Arushi Gupta*, Karan Singh, Wenhan Xia, Elad Hazan. Online Nonstochastic Model-Free Reinforcement Learning. NeuRIPS 2023.
• Nikunj Saunshi, Arushi Gupta, Mark Braverman, Sanjeev Arora. Understanding Influence Functions and Datamodels via Harmonic Analysis. ICLR 2023
• Arushi Gupta * , Nikunj Saunshi * , Dingli Yu * , Kaifeng Lyu, Sanjeev Arora. New Definitions and Evaluations for Saliency Methods : Staying Intrinsic and Sound. NeuRIPS 2022. Oral.
• Yi Zhang, Arushi Gupta, Nikunj Saunshi, Sanjeev Arora. On Predicting Generalization Using GANs. ICLR 2022 spotlight.
• Nikunj Saunshi, Arushi Gupta, Wei Hu. A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning. ICML 2021
• Arushi Gupta, José Manuel Zorilla Matilla, Daniel Hsu , Zoltán Haiman. Non-Gaussian information from weak lensing data via deep learning. Physical Review D 97. 2018.
• Arushi Gupta, Daniel Hsu. Parameter Identification in Markov Chain Choice Models. Published in 28th Conference in Algorithmic Learning Theory. 2017.