Adrian Vladu
9 papers · 2017–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4) π Academic Marathon (6)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(14)
π
Grand Slam
π
Conference Pioneer
Conferences
ICML (4)
AAAI (2)
ICLR (2)
NIPS (1)
Top co-authors
Keywords
convex optimization
(4)
model compression
(1)
differential privacy
(1)
stochastic gradient
(1)
variational inequality
(1)
constrained optimization
(1)
discrete optimization
(1)
sparse approximation
(1)
distributed training
(1)
maximum flow
(1)
parametric optimization
(1)
support vector machine
(1)
convergence guarantee
(1)
bandit optimization
(1)
deep neural network
(1)
accelerated method
(1)
adaptive gradient method
(1)
sparse training
(1)
weight quantization
(1)
neural network sparsity
(1)
Papers
Quantized Distributed Training of Large Models with Convergence Guarantees
ICML 2023
CrAM: A Compression-Aware Minimizer
ICLR 2023
Adaptive Gradient Methods for Constrained Convex Optimization and Variational Inequalities
AAAI 2021
AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
NIPS 2021
Projection-Free Bandit Optimization with Privacy Guarantees
AAAI 2021
Decomposable Submodular Function Minimization via Maximum Flow
ICML 2021
Improved Convergence for $\ell_1$ and $\ell_β$ Regression via Iteratively Reweighted Least Squares
ICML 2019
Towards Deep Learning Models Resistant to Adversarial Attacks
ICLR 2018
Tight Bounds for Approximate CarathΓ©odory and Beyond
ICML 2017