Amartya Sanyal
22 papers · 2018–2025 · 6 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 7 separate collaboration groups - the largest holds only 41% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Amartya Sanyal?
2 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Philip Torr, Puneet K. Dokania, Puneet Dokania
9 papers
· 2018–2024
· ICLR, NeurIPS, ICML
Hide ▲
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
NeurIPS 2024
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
ICML 2023
How robust is unsupervised representation learning to distribution shift?
ICLR 2023
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
NeurIPS 2022
How Benign is Benign Overfitting ?
ICLR 2021
Progressive Skeletonization: Trimming more fat from a network at initialization
ICLR 2021
Calibrating Deep Neural Networks using Focal Loss
NeurIPS 2020
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
ICLR 2020
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
ICML 2018
5 papers whose co-authors appear nowhere else under this name
Protecting against simultaneous data poisoning attacks
ICLR 2025
Provable unlearning in topic modeling and downstream tasks
ICLR 2025
The Role of Learning Algorithms in Collective Action
ICML 2024
A law of adversarial risk, interpolation, and label noise
ICLR 2023
Open Problem: Do you pay for Privacy in Online learning?
COLT 2022