Saunshi, Nikunj

17 publications

ICLR 2025 Efficient Stagewise Pretraining via Progressive Subnetworks Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu, Sobhan Miryoosefi, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

ICML 2025 Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding Tian Jin, Ellie Y Cheng, Zachary Ankner, Nikunj Saunshi, Blake M Elias, Amir Yazdanbakhsh, Jonathan Ragan-Kelley, Suvinay Subramanian, Michael Carbin

ICLR 2025 Reasoning with Latent Thoughts: On the Power of Looped Transformers Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar, Sashank J. Reddi

ICML 2024 Can Looped Transformers Learn to Implement Multi-Step Gradient Descent for In-Context Learning? Khashayar Gatmiry, Nikunj Saunshi, Sashank J. Reddi, Stefanie Jegelka, Sanjiv Kumar

NeurIPS 2024 On the Inductive Bias of Stacking Towards Improving Reasoning Nikunj Saunshi, Stefani Karp, Shankar Krishnan, Sobhan Miryoosefi, Sashank J. Reddi, Sanjiv Kumar

ICML 2023 Task-Specific Skill Localization in Fine-Tuned Language Models Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao, Sanjeev Arora

ICLR 2023 Understanding Influence Functions and Datamodels via Harmonic Analysis Nikunj Saunshi, Arushi Gupta, Mark Braverman, Sanjeev Arora

NeurIPS 2022 New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound Arushi Gupta, Nikunj Saunshi, Dingli Yu, Kaifeng Lyu, Sanjeev Arora

ICLR 2022 On Predicting Generalization Using GANs Yi Zhang, Arushi Gupta, Nikunj Saunshi, Sanjeev Arora

ICML 2022 Understanding Contrastive Learning Requires Incorporating Inductive Biases Nikunj Saunshi, Jordan Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham Kakade, Akshay Krishnamurthy

ICLR 2021 A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks Nikunj Saunshi, Sadhika Malladi, Sanjeev Arora

ICML 2021 A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning Nikunj Saunshi, Arushi Gupta, Wei Hu

NeurIPS 2021 Predicting What You Already Know Helps: Provable Self-Supervised Learning Jason Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo

ICML 2020 A Sample Complexity Separation Between Non-Convex and Convex Meta-Learning Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora

ICML 2020 Provable Representation Learning for Imitation Learning via Bi-Level Optimization Sanjeev Arora, Simon Du, Sham Kakade, Yuping Luo, Nikunj Saunshi

ICML 2019 A Theoretical Analysis of Contrastive Unsupervised Representation Learning Nikunj Saunshi, Orestis Plevrakis, Sanjeev Arora, Mikhail Khodak, Hrishikesh Khandeparkar

ICLR 2018 A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-N-Grams, and LSTMs Sanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli