Amartya Sanyal
22 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Conference Polyglot (6) π§ Keyword Pioneer π Renaissance Researcher (5) π Interdisciplinary Bridge π Academic Marathon (7)
π
Cross-Pollinator
(4)
πΊοΈ
Taxonomy Completionist
(30)
π
Renaissance Researcher
(5)
π
Triple Crown
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(61)
β
The Questioner
(6)
π₯
Unstoppable
(6)
π
Century Club
(22)
Conferences
ICLR (8)
NIPS (5)
ICML (4)
AISTATS (2)
COLT (2)
UAI (1)
Top co-authors
Research topics
Keywords
differential privacy
(4)
lower bound
(2)
online learning
(2)
adversarial learning
(2)
preference optimization
(1)
algorithmic fairness
(1)
adversarial robustness
(1)
direct preference optimization
(1)
certified robustness
(1)
preference alignment
(1)
robust estimation
(1)
sample complexity
(1)
mean estimation
(1)
adversarial training
(1)
mistake bound model
(1)
neural network sparsification
(1)
ensemble learning
(1)
lipschitz continuity
(1)
private data release
(1)
semi-supervised learning
(1)
Papers
Provable unlearning in topic modeling and downstream tasks
ICLR 2025
Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation
AISTATS 2025
Protecting against simultaneous data poisoning attacks
ICLR 2025
Differentially Private Steering for Large Language Model Alignment
ICLR 2025
The Role of Learning Algorithms in Collective Action
ICML 2024
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
COLT 2024
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
NIPS 2024
Robust Mixture Learning when Outliers Overwhelm Small Groups
NIPS 2024
Certified private data release for sparse Lipschitz functions
AISTATS 2024
Provable Privacy with Non-Private Pre-Processing
ICML 2024
A law of adversarial risk, interpolation, and label noise
ICLR 2023
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
ICML 2023
How robust is unsupervised representation learning to distribution shift?
ICLR 2023
Can semi-supervised learning use all the data effectively? A lower bound perspective
NIPS 2023
Open Problem: Do you pay for Privacy in Online learning?
COLT 2022
How unfair is private learning?
UAI 2022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
NIPS 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
NIPS 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