Abhradeep Thakurta
17 papers · 2012–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π§ Keyword Pioneer π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13) π£ Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(13)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π¬
Deep Specialist
(16)
ποΈ
Keyword Collector
(65)
π
Conference Pioneer
π
Trend Setter
π
Century Club
(17)
π₯
Unstoppable
(5)
β‘
Prolific Year
(5)
Conferences
COLT (7)
ICML (5)
AISTATS (3)
AAAI (1)
JMLR (1)
Top co-authors
Research topics
Keywords
differential privacy
(17)
linear regression
(3)
stochastic gradient descent
(3)
sample complexity
(3)
empirical risk minimization
(3)
convex optimization
(3)
regret bound
(2)
matrix completion
(2)
objective perturbation
(2)
online convex programming
(1)
high-dimensional statistics
(1)
low-rank decomposition
(1)
principal component analysis
(1)
deep learning
(1)
machine learning
(1)
bayesian learning
(1)
online convex optimization
(1)
high-dimensional regression
(1)
global convergence
(1)
matrix approximation
(1)
Papers
Private Learning with Public Features
AISTATS 2024
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
AISTATS 2024
Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets
COLT 2023
Differentially Private and Lazy Online Convex Optimization
COLT 2023
(Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping
COLT 2022
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
Private Matrix Approximation and Geometry of Unitary Orbits
COLT 2022
Tempered Sigmoid Activations for Deep Learning with Differential Privacy
AAAI 2021
Evading the Curse of Dimensionality in Unconstrained Private GLMs
AISTATS 2021
(Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces
COLT 2021
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
ICML 2021
Practical and Private (Deep) Learning Without Sampling or Shuffling
ICML 2021
Practical Locally Private Heavy Hitters
JMLR 2020
Differentially Private Matrix Completion Revisited
ICML 2018
Differentially Private Learning with Kernels
ICML 2013
Differentially Private Online Learning
COLT 2012
Private Convex Empirical Risk Minimization and High-dimensional Regression
COLT 2012