Amer Sinha
7 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (12) π£ Hot Topic Early Bird β The Questioner
π
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Application Areas
(4)
Optimization & Theory
(3)
Artificial Intelligence
(2)
Security & Privacy
(2)
Core AI
(2)
Differential Privacy
(2)
Computer Science
(1)
Deep Learning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Applications
(1)
Learning Types Β· Deep Learning
(1)
Learning Types Β· Machine Learning
(1)
Optimization
(1)
Keywords
differential privacy
(5)
poisson subsampling
(3)
adaptive batch linear queries
(2)
machine unlearning
(1)
privacy-preserving learning
(1)
adversarial attack
(1)
model training
(1)
scaling law
(1)
privacy protection
(1)
privacy guarantee
(1)
shuffle mechanism
(1)
utility analysis
(1)
privacy amplification
(1)
privacy accounting
(1)
shuffle model
(1)
model accuracy
(1)
embedding model
(1)
large language model
(1)
gradient sparsity
(1)
private aggregation
(1)
Papers
Balls-and-Bins Sampling for DP-SGD
AISTATS 2025
Scaling Laws for Differentially Private Language Models
ICML 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
How Private are DP-SGD Implementations?
ICML 2024
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
NeurIPS 2024
Sparsity-Preserving Differentially Private Training of Large Embedding Models
NeurIPS 2023
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
ICML 2021