Abhradeep Thakurta
17 papers · 2012–2024 · 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Gold π£ Hot Topic Early Bird
π¬
Deep Specialist
(16)
ποΈ
Keyword Collector
(68)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Conference Pioneer
π
Century Club Β· Bronze
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(17)
Application Areas
(16)
Optimization & Theory
(11)
Security & Privacy
(10)
Core Methods
(8)
Differential Privacy
(8)
Artificial Intelligence
(5)
Mathematics & Optimization
(5)
Learning Types
(5)
Optimization
(4)
Learning Paradigms Β· Artificial Intelligence
(3)
Learning Paradigms Β· Machine Learning
(3)
Data Science & Analytics
(2)
Applications
(2)
Privacy
(2)
Keywords
differential privacy
(17)
linear regression
(3)
sample complexity
(3)
regret bound
(3)
empirical risk minimization
(3)
convex optimization
(3)
stochastic gradient descent
(3)
objective perturbation
(2)
matrix completion
(2)
online convex programming
(1)
high-dimensional statistics
(1)
low-rank decomposition
(1)
principal component analysis
(1)
deep learning
(1)
online convex optimization
(1)
bayesian learning
(1)
convex loss
(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
Differentially Private and Lazy Online Convex Optimization
COLT 2023
Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets
COLT 2023
(Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping
COLT 2022
Private Matrix Approximation and Geometry of Unitary Orbits
COLT 2022
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
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
Practical and Private (Deep) Learning Without Sampling or Shuffling
ICML 2021
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
ICML 2021
Tempered Sigmoid Activations for Deep Learning with Differential Privacy
AAAI 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