Thomas Steinke
28 papers · 2015–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Cross-Pollinator (10) π Academic Marathon (10) π Interdisciplinary Bridge π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (27)
πΊοΈ
Taxonomy Completionist
(27)
π§
Keyword Pioneer
π¬
Deep Specialist
(15)
π
Triple Crown
π
Keyword Champion
(2)
π
Trend Setter
π
Century Club
(28)
ποΈ
Keyword Collector
(96)
β‘
Prolific Year
(5)
β
The Questioner
π₯
Unstoppable
(9)
Conferences
NIPS (9)
COLT (7)
ICML (6)
ICLR (5)
AISTATS (1)
Top co-authors
Research topics
Keywords
differential privacy
(18)
statistical query
(5)
generalization bound
(4)
conditional mutual information
(2)
private model training
(2)
vc dimension
(2)
generalization guarantee
(2)
public datum
(2)
private algorithm
(2)
adaptive query
(2)
stochastic gradient descent
(2)
sample complexity
(1)
convex optimization
(1)
pac learning
(1)
kl divergence
(1)
knowledge transfer
(1)
transfer learning
(1)
stochastic optimization
(1)
optimal transport
(1)
privacy-preserving learning
(1)
Papers
Near-Exact Privacy Amplification for Matrix Mechanisms
ICLR 2025
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
ICLR 2025
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
ICLR 2024
Privacy Amplification for Matrix Mechanisms
ICLR 2024
Stealing part of a production language model
ICML 2024
Private Geometric Median
NIPS 2024
Privacy Auditing with One (1) Training Run
NIPS 2023
Faster Differentially Private Convex Optimization via Second-Order Methods
NIPS 2023
Why Is Public Pretraining Necessary for Private Model Training?
ICML 2023
Counting Distinct Elements Under Person-Level Differential Privacy
NIPS 2023
Hyperparameter Tuning with Renyi Differential Privacy
ICLR 2022
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
A Private and Computationally-Efficient Estimator for Unbounded Gaussians
COLT 2022
Leveraging Public Data for Practical Private Query Release
ICML 2021
Evading the Curse of Dimensionality in Unconstrained Private GLMs
AISTATS 2021
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
COLT 2021
Privately Learning Subspaces
NIPS 2021
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
ICML 2021
Open Problem: Information Complexity of VC Learning
COLT 2020
The Discrete Gaussian for Differential Privacy
NIPS 2020
Reasoning About Generalization via Conditional Mutual Information
COLT 2020
New Oracle-Efficient Algorithms for Private Synthetic Data Release
ICML 2020
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
NIPS 2019
Private Hypothesis Selection
NIPS 2019
Calibrating Noise to Variance in Adaptive Data Analysis
COLT 2018
The Limits of Post-Selection Generalization
NIPS 2018
Generalization for Adaptively-chosen Estimators via Stable Median
COLT 2017
Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery
COLT 2015