Abhradeep Guha Thakurta
28 papers · 2013–2025 · 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (33) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π¬
Deep Specialist
(20)
π
Triple Crown
π
Keyword Champion
(2)
π§
Keyword Pioneer
π
Trend Setter
β
The Questioner
(2)
ποΈ
Keyword Collector
(110)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
Venues
Top co-authors
Research topics
Machine Learning
(25)
Application Areas
(20)
Optimization & Theory
(15)
Artificial Intelligence
(10)
Security & Privacy
(9)
Mathematics & Optimization
(7)
Differential Privacy
(6)
Learning Paradigms Β· Artificial Intelligence
(6)
Learning Types
(6)
Optimization
(6)
Core AI
(5)
Core Methods
(4)
Deep Learning
(3)
Privacy
(3)
Learning Paradigms Β· Machine Learning
(2)
Keywords
differential privacy
(23)
stochastic gradient descent
(5)
privacy amplification
(4)
federated learning
(3)
matrix factorization
(3)
linear regression
(3)
matrix mechanism
(3)
differentially private
(2)
convex optimization
(2)
non-convex optimization
(2)
user-level privacy
(2)
regret bound
(2)
sample complexity
(2)
feature selection
(2)
excess risk
(2)
private training
(2)
online learning
(2)
lasso estimator
(2)
logistic regression
(1)
multi-task learning
(1)
Papers
Near-Exact Privacy Amplification for Matrix Mechanisms
ICLR 2025
Near-Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large Batches
ALT 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
Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
ICML 2024
Privacy Amplification for Matrix Mechanisms
ICLR 2024
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
ICML 2024
(Amplified) Banded Matrix Factorization: A unified approach to private training
NeurIPS 2023
Faster Differentially Private Convex Optimization via Second-Order Methods
NeurIPS 2023
Measuring Forgetting of Memorized Training Examples
ICLR 2023
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
ICML 2023
Multi-Task Differential Privacy Under Distribution Skew
ICML 2023
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
NeurIPS 2023
Training Private Models That Know What They Donβt Know
NeurIPS 2023
Why Is Public Pretraining Necessary for Private Model Training?
ICML 2023
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
NeurIPS 2022
When Does Differentially Private Learning Not Suffer in High Dimensions?
NeurIPS 2022
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks
NeurIPS 2021
Differentially Private Model Personalization
NeurIPS 2021
Privacy Amplification via Random Check-Ins
NeurIPS 2020
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
NeurIPS 2020
Private Stochastic Convex Optimization with Optimal Rates
NeurIPS 2019
Model-Agnostic Private Learning
NeurIPS 2018
Practical Locally Private Heavy Hitters
NeurIPS 2017
Nearly Optimal Private LASSO
NeurIPS 2015
(Near) Dimension Independent Risk Bounds for Differentially Private Learning
ICML 2014
Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso
COLT 2013
(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings
NeurIPS 2013