Dominik Stöger
5 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
COLT (2)
NIPS (2)
ICLR (1)
Top co-authors
Keywords
gradient descent
(2)
overparameterized model
(2)
global optimization
(1)
l1 regularization
(1)
low-rank matrix recovery
(1)
spectral learning
(1)
linear convergence
(1)
low-rank matrix reconstruction
(1)
basis pursuit
(1)
spectral method
(1)
implicit regularization
(1)
generalization guarantee
(1)
matrix sensing
(1)
iteratively reweighted least square
(1)
learning theory
(1)
implicit spectral bia
(1)
sparse recovery
(1)
Papers
Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity Extended Abstract
COLT 2025
Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing
COLT 2023
Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate
NIPS 2021
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
NIPS 2021
Understanding Over-parameterization in Generative Adversarial Networks
ICLR 2021