Amartya Sanyal

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 48

Top Topics

Top Venues

Publications

Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study. CoRR (2024)
Daniil Dmitriev, Kristóf Szabó, Amartya Sanyal
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective. CoRR (2024)
Daniil Dmitriev, Kristóf Szabó, Amartya Sanyal
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective. COLT (2024)
Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang
Certified private data release for sparse Lipschitz functions. AISTATS (2024)
Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal
PILLAR: How to make semi-private learning more effective. SaTML (2024)
Shashwat Goel, Ameya Prabhu, Philip H. S. Torr, Ponnurangam Kumaraguru, Amartya Sanyal
Corrective Machine Unlearning. CoRR (2024)
Amartya Sanyal, Yaxi Hu, Yaodong Yu, Yian Ma, Yixin Wang, Bernhard Schölkopf
Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation. CoRR (2024)
Omri Ben-Dov, Jake Fawkes, Samira Samadi, Amartya Sanyal
The Role of Learning Algorithms in Collective Action. CoRR (2024)
Daniil Dmitriev, Rares-Darius Buhai, Stefan Tiegel, Alexander Wolters, Gleb Novikov, Amartya Sanyal, David Steurer, Fanny Yang
Robust Mixture Learning when Outliers Overwhelm Small Groups. CoRR (2024)
Yaxi Hu, Amartya Sanyal, Bernhard Schölkopf
Provable Privacy with Non-Private Pre-Processing. CoRR (2024)
Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang
Sample-efficient private data release for Lipschitz functions under sparsity assumptions. CoRR (2023)
Daniel Paleka, Amartya Sanyal
A law of adversarial risk, interpolation, and label noise. ICLR (2023)
Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip Torr
Catastrophic overfitting can be induced with discriminative non-robust features. Trans. Mach. Learn. Res. 2023 (2023)
Yuge Shi, Imant Daunhawer, Julia E. Vogt, Philip H. S. Torr, Amartya Sanyal
How robust is unsupervised representation learning to distribution shift? ICLR (2023)
Alexandru Tifrea, Gizem Yüce, Amartya Sanyal, Fanny Yang
Can semi-supervised learning use all the data effectively? A lower bound perspective. NeurIPS (2023)
Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal
PILLAR: How to make semi-private learning more effective. CoRR (2023)
Alexandru Tifrea, Gizem Yüce, Amartya Sanyal, Fanny Yang
Can semi-supervised learning use all the data effectively? A lower bound perspective. CoRR (2023)
Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi
Certifying Ensembles: A General Certification Theory with S-Lipschitzness. CoRR (2023)
Piersilvio De Bartolomeis, Jacob Clarysse, Amartya Sanyal, Fanny Yang
How robust accuracy suffers from certified training with convex relaxations. CoRR (2023)
Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi
Certifying Ensembles: A General Certification Theory with S-Lipschitzness. ICML (2023)
Amartya Sanyal, Giorgia Ramponi
Do you pay for Privacy in Online learning? CoRR (2022)
Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. CoRR (2022)
Daniel Paleka, Amartya Sanyal
A law of adversarial risk, interpolation, and label noise. CoRR (2022)
Yuge Shi, Imant Daunhawer, Julia E. Vogt, Philip H. S. Torr, Amartya Sanyal
How robust are pre-trained models to distribution shift? CoRR (2022)
Amartya Sanyal, Yaxi Hu, Fanny Yang
How unfair is private learning? UAI (2022)
Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip H. S. Torr
Catastrophic overfitting is a bug but also a feature. CoRR (2022)
Pau de Jorge Aranda, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. NeurIPS (2022)
Amartya Sanyal, Yaxi Hu, Fanny Yang
How unfair is private learning ? CoRR (2022)
Amartya Sanyal
Identifying and Exploiting Structures for Reliable Deep Learning. CoRR (2021)
Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
Progressive Skeletonization: Trimming more fat from a network at initialization. ICLR (2021)
Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr
How Benign is Benign Overfitting ? ICLR (2021)
Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania
Calibrating Deep Neural Networks using Focal Loss. CoRR (2020)
Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr
How benign is benign overfitting? CoRR (2020)
Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania
Calibrating Deep Neural Networks using Focal Loss. NeurIPS (2020)
Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. ICLR (2020)
Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
Progressive Skeletonization: Trimming more fat from a network at initialization. CoRR (2020)
Ahmed Ibrahim S. Khalil, Costerwell Khyriem, Anupam Chattopadhyay, Amartya Sanyal
Hierarchical discovery of large-scale and focal copy number alterations in low-coverage cancer genomes. BMC Bioinform. 21 (1) (2020)
Ahmed Ibrahim S. Khalil, Siti Rawaidah Binte Mohammad Muzaki, Anupam Chattopadhyay, Amartya Sanyal
Identification and utilization of copy number information for correcting Hi-C contact map of cancer cell lines. BMC Bioinform. 21 (1) (2020)
Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. CoRR (2019)
Amartya Sanyal, Pawan Kumar, Purushottam Kar, Sanjay Chawla, Fabrizio Sebastiani
Optimizing non-decomposable measures with deep networks. Mach. Learn. 107 (8-10) (2018)
Amartya Sanyal, Varun Kanade, Philip H. S. Torr
Low Rank Structure of Learned Representations. CoRR (2018)
Amartya Sanyal, Matt J. Kusner, Adrià Gascón, Varun Kanade
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service. ICML (2018)
Amartya Sanyal, Pawan Kumar, Purushottam Kar, Sanjay Chawla, Fabrizio Sebastiani
Optimizing Non-decomposable Measures with Deep Networks. CoRR (2018)
Amartya Sanyal, Matt J. Kusner, Adrià Gascón, Varun Kanade
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service. CoRR (2018)
Amartya Sanyal, Sanjana Garg, Asim Unmesh, Harish Karnick
Agent based simulation of the evolution of society as an alternate maximzation problem. BESC (2017)
Amartya Sanyal, Sanjana Garg, Asim Unmesh
Agent based simulation of the evolution of society as an alternate maximization problem. CoRR (2017)
Bart van Merriënboer, Amartya Sanyal, Hugo Larochelle, Yoshua Bengio
Multiscale sequence modeling with a learned dictionary. CoRR (2017)
Amartya Sanyal, Ujjwal Bhattacharya, Swapan K. Parui
A Hybrid Deep Architecture for Face Recognition in Real-Life Scenario. ICVGIP Workshops (2016)