Badih Ghazi
36 papers · 2019–2025 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot (10) π§ Keyword Pioneer π Interdisciplinary Bridge π Academic Marathon (6)
π
Cross-Pollinator
(14)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(35)
π
Triple Crown
π
Grand Slam
π¬
Deep Specialist
(22)
π
Keyword Champion
(2)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(115)
β
The Questioner
π₯
Unstoppable
(7)
π
Century Club
(36)
Conferences
NIPS (12)
ICML (9)
COLT (4)
ICLR (3)
AAAI (2)
AISTATS (2)
AACL (1)
ALT (1)
EMNLP (1)
IJCNLP (1)
Top co-authors
Research topics
Keywords
differential privacy
(20)
stochastic gradient descent
(3)
neural network
(3)
privacy-preserving learning
(2)
local model
(2)
convex optimization
(2)
user-level privacy
(2)
approximation algorithm
(2)
k-means clustering
(2)
logical reasoning
(2)
stochastic convex optimization
(2)
large language model
(2)
privacy-preserving algorithm
(2)
gradient sparsity
(2)
shuffle model
(2)
statistical estimation
(2)
randomized response
(2)
distributed learning
(1)
bert model
(1)
pac learning
(1)
Papers
Scaling Laws for Differentially Private Language Models
ICML 2025
On Memorization of Large Language Models in Logical Reasoning
AACL 2025
Balls-and-Bins Sampling for DP-SGD
AISTATS 2025
On Memorization of Large Language Models in Logical Reasoning
IJCNLP 2025
PREM: Privately Answering Statistical Queries with Relative Error
COLT 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
How Private are DP-SGD Implementations?
ICML 2024
Differentially Private Optimization with Sparse Gradients
NIPS 2024
LabelDP-Pro: Learning with Label Differential Privacy via Projections
ICLR 2024
Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization
ICML 2024
On Convex Optimization with Semi-Sensitive Features
COLT 2024
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
NIPS 2024
On User-Level Private Convex Optimization
ICML 2023
On Computing Pairwise Statistics with Local Differential Privacy
NIPS 2023
Optimal Unbiased Randomizers for Regression with Label Differential Privacy
NIPS 2023
On Differentially Private Sampling from Gaussian and Product Distributions
NIPS 2023
Differentially Private Heatmaps
AAAI 2023
Regression with Label Differential Privacy
ICLR 2023
Ticketed LearningβUnlearning Schemes
COLT 2023
Sparsity-Preserving Differentially Private Training of Large Embedding Models
NIPS 2023
User-Level Differential Privacy With Few Examples Per User
NIPS 2023
Anonymized Histograms in Intermediate Privacy Models
NIPS 2022
Private Isotonic Regression
NIPS 2022
Faster Privacy Accounting via Evolving Discretization
ICML 2022
Private Rank Aggregation in Central and Local Models
AAAI 2022
Large-Scale Differentially Private BERT
EMNLP 2022
On Avoiding the Union Bound When Answering Multiple Differentially Private Queries
COLT 2021
User-Level Differentially Private Learning via Correlated Sampling
NIPS 2021
Deep Learning with Label Differential Privacy
NIPS 2021
Robust and Private Learning of Halfspaces
AISTATS 2021
Near-tight Closure Bounds for the Littlestone and Threshold Dimensions
ALT 2021
Locally Private k-Means in One Round
ICML 2021
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
ICML 2021
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead
ICML 2020
Differentially Private Clustering: Tight Approximation Ratios
NIPS 2020
Recursive Sketches for Modular Deep Learning
ICML 2019