| 2025 | ICLR | Efficient stagewise pretraining via progressive subnetworks. | Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu, Sobhan Miryoosefi, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar |
| 2025 | ICLR | Reasoning with Latent Thoughts: On the Power of Looped Transformers. | Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar, Sashank J. Reddi |
| 2025 | ICML | 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 |
| 2024 | ICML | 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 |
| 2023 | ACL | Reasoning in Large Language Models Through Symbolic Math Word Problems. | Vedant Gaur, Nikunj Saunshi |
| 2023 | ICLR | Understanding Influence Functions and Datamodels via Harmonic Analysis. | Nikunj Saunshi, Arushi Gupta, Mark Braverman, Sanjeev Arora |
| 2023 | ICML | Task-Specific Skill Localization in Fine-tuned Language Models. | Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao, Sanjeev Arora |
| 2022 | ICLR | On Predicting Generalization using GANs. | Yi Zhang, Arushi Gupta, Nikunj Saunshi, Sanjeev Arora |
| 2022 | ICML | Understanding Contrastive Learning Requires Incorporating Inductive Biases. | Nikunj Saunshi, Jordan T. Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham M. Kakade, Akshay Krishnamurthy |
| 2021 | ICLR | A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks. | Nikunj Saunshi, Sadhika Malladi, Sanjeev Arora |
| 2021 | ICML | A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning. | Nikunj Saunshi, Arushi Gupta, Wei Hu |
| 2020 | ICML | Provable Representation Learning for Imitation Learning via Bi-level Optimization. | Sanjeev Arora, Simon S. Du, Sham M. Kakade, Yuping Luo, Nikunj Saunshi |
| 2020 | ICML | A Sample Complexity Separation between Non-Convex and Convex Meta-Learning. | Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora |
| 2019 | ICML | A Theoretical Analysis of Contrastive Unsupervised Representation Learning. | Nikunj Saunshi, Orestis Plevrakis, Sanjeev Arora, Mikhail Khodak, Hrishikesh Khandeparkar |
| 2018 | ACL | A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. | Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora |
| 2018 | ICLR | A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs. | Sanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli |
| 2018 | LREC | A Large Self-Annotated Corpus for Sarcasm. | Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli |