Thomas Steinke
29 papers · 2015–2026 · 5 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (32) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π¬
Deep Specialist
(17)
π
Triple Crown
π
Keyword Champion
(2)
β‘
Prolific Year Β· Productive
π
Trend Setter
β
The Questioner
π₯
Unstoppable Β· Silver
ποΈ
Keyword Collector
(126)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(27)
Application Areas
(17)
Optimization & Theory
(17)
Security & Privacy
(11)
Artificial Intelligence
(9)
Differential Privacy
(9)
Mathematics & Optimization
(8)
Core AI
(6)
Mathematics
(6)
Core Methods
(4)
Learning Paradigms
(3)
Learning Types
(3)
Optimization
(2)
Privacy
(2)
Deep Learning
(1)
Keywords
differential privacy
(23)
statistical query
(5)
generalization bound
(4)
stochastic gradient descent
(3)
vc dimension
(3)
sensitivity bound
(2)
adaptive query
(2)
private model training
(2)
privacy auditing
(2)
generalization guarantee
(2)
privacy leakage
(2)
privacy amplification
(2)
conditional mutual information
(2)
matrix mechanism
(2)
uniform convergence
(2)
private algorithm
(2)
mean estimation
(2)
linear regression
(2)
public data
(2)
kl divergence
(1)
Papers
Privately Estimating Black-Box Statistics
COLT 2026
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
Private Geometric Median
NeurIPS 2024
Stealing part of a production language model
ICML 2024
Counting Distinct Elements Under Person-Level Differential Privacy
NeurIPS 2023
Faster Differentially Private Convex Optimization via Second-Order Methods
NeurIPS 2023
Privacy Auditing with One (1) Training Run
NeurIPS 2023
Why Is Public Pretraining Necessary for Private Model Training?
ICML 2023
A Private and Computationally-Efficient Estimator for Unbounded Gaussians
COLT 2022
Hyperparameter Tuning with Renyi Differential Privacy
ICLR 2022
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
Evading the Curse of Dimensionality in Unconstrained Private GLMs
AISTATS 2021
Leveraging Public Data for Practical Private Query Release
ICML 2021
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
COLT 2021
Privately Learning Subspaces
NeurIPS 2021
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
ICML 2021
New Oracle-Efficient Algorithms for Private Synthetic Data Release
ICML 2020
Open Problem: Information Complexity of VC Learning
COLT 2020
Reasoning About Generalization via Conditional Mutual Information
COLT 2020
The Discrete Gaussian for Differential Privacy
NeurIPS 2020
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
NeurIPS 2019
Private Hypothesis Selection
NeurIPS 2019
Calibrating Noise to Variance in Adaptive Data Analysis
COLT 2018
The Limits of Post-Selection Generalization
NeurIPS 2018
Generalization for Adaptively-chosen Estimators via Stable Median
COLT 2017
Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery
COLT 2015