Sanyal, Amartya

37 publications

TMLR 2026 Delta-Influence: Identifying Poisons via Influence Functions Wenjie Li, Jiawei Li, Pengcheng Zeng, Christian Schroeder de Witt, Ameya Prabhu, Amartya Sanyal

AISTATS 2025 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 Schölkopf

NeurIPS 2025 An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise Johanna Düngler, Amartya Sanyal

ICLR 2025 Differentially Private Steering for Large Language Model Alignment Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal

ICLR 2025 Protecting Against Simultaneous Data Poisoning Attacks Neel Alex, Shoaib Ahmed Siddiqui, Amartya Sanyal, David Krueger

ICLR 2025 Provable Unlearning in Topic Modeling and Downstream Tasks Stanley Wei, Sadhika Malladi, Sanjeev Arora, Amartya Sanyal

ICMLW 2024 Accuracy on the Wrong Line: On the Pitfalls of Noisy Data for OOD Generalisation Amartya Sanyal, Yaxi Hu, Yaodong Yu, Yian Ma, Yixin Wang, Bernhard Schölkopf

AISTATS 2024 Certified Private Data Release for Sparse Lipschitz Functions Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang

TMLR 2024 Corrective Machine Unlearning Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal

COLT 2024 On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective Daniil Dmitriev, Kristóf Szabó, Amartya Sanyal

ICML 2024 Provable Privacy with Non-Private Pre-Processing Yaxi Hu, Amartya Sanyal, Bernhard Schölkopf

NeurIPSW 2024 Provable Unlearning in Topic Modeling and Downstream Tasks Stanley Wei, Sadhika Malladi, Sanjeev Arora, Amartya Sanyal

NeurIPS 2024 Robust Mixture Learning When Outliers Overwhelm Small Groups Daniil Dmitriev, Rares-Darius Buhai, Stefan Tiegel, Alexander Wolters, Gleb Novikov, Amartya Sanyal, David Steurer, Fanny Yang

ICML 2024 The Role of Learning Algorithms in Collective Action Omri Ben-Dov, Jake Fawkes, Samira Samadi, Amartya Sanyal

ICMLW 2024 Unveiling CLIP Dynamics: Linear Mode Connectivity and Generalization Alireza Abdollahpourrostam, Amartya Sanyal, Seyed-Mohsen Moosavi-Dezfooli

NeurIPS 2024 What Makes and Breaks Safety Fine-Tuning? a Mechanistic Study Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H.S. Torr, Amartya Sanyal, Puneet K. Dokania

ICMLW 2024 What Makes and Breaks Safety Fine-Tuning? a Mechanistic Study Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip Torr, Amartya Sanyal, Puneet K. Dokania

ICLR 2023 A Law of Adversarial Risk, Interpolation, and Label Noise Daniel Paleka, Amartya Sanyal

NeurIPS 2023 Can Semi-Supervised Learning Use All the Data Effectively? a Lower Bound Perspective Alexandru Tifrea, Gizem Yüce, Amartya Sanyal, Fanny Yang

TMLR 2023 Catastrophic Overfitting Can Be Induced with Discriminative Non-Robust Features Guillermo Ortiz-Jimenez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip Torr

ICML 2023 Certifying Ensembles: A General Certification Theory with S-Lipschitzness Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip Torr, Adel Bibi

ICMLW 2023 Certifying Ensembles: A General Certification Theory with S-Lipschitzness Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip Torr, Adel Bibi

ICLR 2023 How Robust Is Unsupervised Representation Learning to Distribution Shift? Yuge Shi, Imant Daunhawer, Julia E Vogt, Philip Torr, Amartya Sanyal

ICLRW 2023 How to Make Semi-Private Learning Effective Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal

NeurIPSW 2022 Certified Defences Hurt Generalisation Piersilvio De Bartolomeis, Jacob Clarysse, Fanny Yang, Amartya Sanyal

NeurIPSW 2022 Certified Defences Hurt Generalisation Piersilvio De Bartolomeis, Jacob Clarysse, Fanny Yang, Amartya Sanyal

ICMLW 2022 How Robust Are Pre-Trained Models to Distribution Shift? Yuge Shi, Imant Daunhawer, Julia E Vogt, Philip Torr, Amartya Sanyal

ICMLW 2022 How Robust Are Pre-Trained Models to Distribution Shift? Yuge Shi, Imant Daunhawer, Julia E Vogt, Philip Torr, Amartya Sanyal

UAI 2022 How Unfair Is Private Learning? Amartya Sanyal, Yaxi Hu, Fanny Yang

NeurIPS 2022 Make Some Noise: Reliable and Efficient Single-Step Adversarial Training Pau de Jorge Aranda, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip Torr, Gregory Rogez, Puneet Dokania

COLT 2022 Open Problem: Do You Pay for Privacy in Online Learning? Amartya Sanyal, Giorgia Ramponi

ICLR 2021 How Benign Is Benign Overfitting ? Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip Torr

ICLR 2021 Progressive Skeletonization: Trimming More Fat from a Network at Initialization Pau de Jorge, Amartya Sanyal, Harkirat Behl, Philip Torr, Grégory Rogez, Puneet K. Dokania

NeurIPS 2020 Calibrating Deep Neural Networks Using Focal Loss Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip Torr, Puneet Dokania

ICLR 2020 Stable Rank Normalization for Improved Generalization in Neural Networks and GANs Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania

MLJ 2018 Optimizing Non-Decomposable Measures with Deep Networks Amartya Sanyal, Pawan Kumar, Purushottam Kar, Sanjay Chawla, Fabrizio Sebastiani

ICML 2018 TAPAS: Tricks to Accelerate (encrypted) Prediction as a Service Amartya Sanyal, Matt Kusner, Adria Gascon, Varun Kanade