Arda Sahiner
7 papers · 2021–2024 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
ICLR (5)
ICML (2)
Top co-authors
Keywords
convex optimization
(2)
vision transformer
(1)
attention mechanism
(1)
proximal gradient
(1)
relu network
(1)
convex duality
(1)
two-layer neural network
(1)
low rank
(1)
low-rank regularization
(1)
token clustering
(1)
gated relu
(1)
polyhedral cone constraint
(1)
accelerated proximal gradient
(1)
group-l1 regularization
(1)
augmented lagrangian
(1)
cone decomposition
(1)
Papers
Scaling Convex Neural Networks with Burer-Monteiro Factorization
ICLR 2024
Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
ICLR 2022
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization
ICLR 2022
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
ICML 2022
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers
ICML 2022
Convex Regularization behind Neural Reconstruction
ICLR 2021
Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms
ICLR 2021