Amer Sinha
7 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10)
🌈
Renaissance Researcher
(5)
❓
The Questioner
Conferences
ICML (3)
NIPS (2)
AISTATS (1)
ICLR (1)
Top co-authors
Research topics
Keywords
differential privacy
(3)
stochastic gradient descent
(1)
distributed learning
(1)
privacy-preserving learning
(1)
model training
(1)
privacy guarantee
(1)
poisson subsampling
(1)
shuffle mechanism
(1)
utility analysis
(1)
shuffle model
(1)
embedding model
(1)
gradient sparsity
(1)
private aggregation
(1)
adaptive batch linear queries
(1)
Papers
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
Balls-and-Bins Sampling for DP-SGD
AISTATS 2025
Scaling Laws for Differentially Private Language Models
ICML 2025
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
NIPS 2024
How Private are DP-SGD Implementations?
ICML 2024
Sparsity-Preserving Differentially Private Training of Large Embedding Models
NIPS 2023
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
ICML 2021