| 2026 | SODA | Learning in an Echo Chamber: Online Learning with Replay Adversary. | Daniil Dmitriev, Harald Eskelund Franck, Carolin Heinzler, Amartya Sanyal |
| 2025 | AISTATS | Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation. | Amartya Sanyal, Yaxi Hu, Yaodong Yu, Yian Ma, Yixin Wang, Bernhard Schlkopf |
| 2025 | ICLR | Protecting against simultaneous data poisoning attacks. | Neel Alex, Shoaib Ahmed Siddiqui, Amartya Sanyal, David Krueger |
| 2025 | ICLR | Differentially Private Steering for Large Language Model Alignment. | Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal |
| 2025 | ICLR | Provable unlearning in topic modeling and downstream tasks. | Stanley Wei, Sadhika Malladi, Sanjeev Arora, Amartya Sanyal |
| 2024 | AISTATS | Certified private data release for sparse Lipschitz functions. | Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hnig, Fanny Yang |
| 2024 | COLT | On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective. | Daniil Dmitriev, Kristf Szab, Amartya Sanyal |
| 2024 | ICML | The Role of Learning Algorithms in Collective Action. | Omri Ben-Dov, Jake Fawkes, Samira Samadi, Amartya Sanyal |
| 2024 | ICML | Provable Privacy with Non-Private Pre-Processing. | Yaxi Hu, Amartya Sanyal, Bernhard Schlkopf |
| 2023 | ICLR | A law of adversarial risk, interpolation, and label noise. | Daniel Paleka, Amartya Sanyal |
| 2023 | ICLR | How robust is unsupervised representation learning to distribution shift? | Yuge Shi, Imant Daunhawer, Julia E. Vogt, Philip H. S. Torr, Amartya Sanyal |
| 2023 | ICML | Certifying Ensembles: A General Certification Theory with S-Lipschitzness. | Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi |
| 2022 | UAI | How unfair is private learning? | Amartya Sanyal, Yaxi Hu, Fanny Yang |
| 2021 | ICLR | Progressive Skeletonization: Trimming more fat from a network at initialization. | Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grgory Rogez, Puneet K. Dokania |
| 2021 | ICLR | How Benign is Benign Overfitting ? | Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr |
| 2020 | ICLR | Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. | Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania |
| 2018 | ICML | TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service. | Amartya Sanyal, Matt J. Kusner, Adri Gascn, Varun Kanade |