← Authors

Tolga Ergen

16 papers · 2020–2025 · 6 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (19) 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🀝 Dynamic Duo (15) ⚑ Prolific Year (5) πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (16)

Conferences

ICLR (7) ICML (4) NIPS (2) AISTATS (1) JMLR (1) NAACL (1)

Top co-authors

Mert Pilanci (15) Arda Sahiner (5) Morteza Mardani (4) Batu Ozturkler (4) John M. Pauly (4) John Pauly (1) Jin Huang (1) Jonathan Lacotte (1) Honglak Lee (1) Qijia Liu (1)

Keywords

convex optimization (8) relu network (4) neural network (3) spline interpolation (3) representation learning (2) deep neural network (2) weight decay (2) convex duality (2) text summarization (1) neural network optimization (1) group lasso (1) semi-definite programming (1) multiple kernel learning (1) semi-definite program (1) relu activation (1) benchmark dataset (1) neural collapse (1) gradient flow (1) weight decay regularization (1) gated relu network (1)

Papers

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows NAACL 2025
Scaling Convex Neural Networks with Burer-Monteiro Factorization ICLR 2024
Parallel Deep Neural Networks Have Zero Duality Gap ICLR 2023
Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks NIPS 2023
Globally Optimal Training of Neural Networks with Threshold Activation Functions ICLR 2023
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs NIPS 2023
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization ICLR 2022
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers ICML 2022
Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions ICLR 2022
Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021
Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time ICLR 2021
Convex Geometry and Duality of Over-parameterized Neural Networks JMLR 2021
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs ICML 2021
Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms ICLR 2021
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks ICML 2020
Convex Geometry of Two-Layer ReLU Networks: Implicit Autoencoding and Interpretable Models AISTATS 2020